© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8325
    Prev
    Next
    INDEX
    Explanations

    references to different TV shows and their ratings, as well as information related to media events and controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    167
    +0.21
    0.7%
    232
    +0.15
    0.5%
    137
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.21
    0.06
    288
    +0.15
    0.07
    167
    +0.14
    0.02
    Negative Logits
    EStream
    -1.25
    WT
    -1.12
    lihood
    -1.09
     guiActiveUn
    -1.05
    OPLE
    -1.01
    GBT
    -0.98
    STER
    -0.98
    terday
    -0.95
    76561
    -0.93
    WARE
    -0.92
    POSITIVE LOGITS
    ainers
    1.79
    ributed
    1.56
    rast
    1.41
    roversial
    1.40
    ainment
    1.37
    ribution
    1.36
    iguous
    1.30
    ribute
    1.27
    rary
    1.26
    ains
    1.23
    Activations Density 0.885%

    No Known Activations