© 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 Local
    9. 6-RES_SCL-AJT
    11. 31999
    Prev
    Next
    INDEX
    Explanations

    references to specific names, likely related to media coverage or storytelling

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.18
    0.7%
    213
    +0.13
    0.5%
    351
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.18
    631
    +0.13
    0.08
    311
    +0.12
    -0.04
    Negative Logits
     Kubrick
    -0.84
     Iceland
    -0.80
     Icelandic
    -0.80
    lihood
    -0.79
     Elves
    -0.77
     royalties
    -0.75
    ãģį
    -0.75
     ASC
    -0.74
     Idle
    -0.73
    aird
    -0.73
    POSITIVE LOGITS
    phasis
    1.51
    otions
    1.46
    otional
    1.45
    igrant
    1.44
    otion
    1.42
    brace
    1.37
    igrants
    1.34
    igration
    1.33
    phas
    1.30
    blems
    1.30
    Activations Density 9.354%

    No Known Activations