© 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. 35678
    Prev
    Next
    INDEX
    Explanations

    different versions or iterations of something within a story or context

    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
    +0.24
    1.1%
    679
    +0.11
    0.5%
    571
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.24
    0.09
    571
    +0.11
    0.09
    679
    +0.10
    0.16
    Negative Logits
    usters
    -0.91
    redo
    -0.71
    veyard
    -0.68
    oros
    -0.67
    ãĤī
    -0.65
    iencies
    -0.65
    reditary
    -0.65
    ãĥ©ãĥ³
    -0.64
    inently
    -0.64
    eneg
    -0.62
    POSITIVE LOGITS
     thereof
    1.07
     version
    0.86
     versions
    0.77
    UID
    0.77
    lihood
    0.71
     of
    0.69
    que
    0.62
     paste
    0.62
    Versions
    0.61
     Scroll
    0.60
    Activations Density 7.785%

    No Known Activations