© 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 EvalsExportsAPI 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. 33734
    Prev
    Next
    INDEX
    Explanations

    words that appear to be nonsensical strings of characters, potentially indicating an issue with encoding or formatting

    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
    659
    +0.17
    0.6%
    679
    +0.16
    0.6%
    14
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.10
    247
    +0.16
    0.08
    403
    +0.15
    0.06
    Negative Logits
    FFFF
    -0.86
    DIT
    -0.83
     Winchester
    -0.81
     Winc
    -0.79
    mpeg
    -0.77
     poppy
    -0.77
    LOAD
    -0.76
     halves
    -0.74
     Adin
    -0.73
    IVER
    -0.72
    POSITIVE LOGITS
    achu
    1.64
    ernels
    1.48
    ernel
    1.47
    yu
    1.37
    owski
    1.27
    hs
    1.26
    ileaks
    1.26
    atana
    1.23
    ku
    1.21
    atsu
    1.21
    Activations Density 7.982%

    No Known Activations