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

    Neuronpedia

    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. 40572
    Prev
    Next
    INDEX
    Explanations

    statistical terms and figures

    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
    +0.19
    1.0%
    195
    +0.12
    0.6%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.19
    0.09
    155
    +0.12
    0.08
    268
    +0.10
    0.03
    Negative Logits
    ipop
    -0.63
    hops
    -0.63
    uthor
    -0.60
     safely
    -0.59
    NetMessage
    -0.59
     passively
    -0.59
     diligently
    -0.58
    «ĺ
    -0.57
    annis
    -0.56
     hemor
    -0.55
    POSITIVE LOGITS
     contrasts
    1.04
     stark
    0.98
     contrast
    0.94
    ly
    0.88
     contrasting
    0.75
    itudinal
    0.71
    eting
    0.70
     outlines
    0.70
    er
    0.69
     Contrast
    0.69
    Activations Density 6.222%

    No Known Activations