Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13311
    Prev
    Next
    INDEX
    Explanations

    websites and online references in a variety of subjects

    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
    77
    +0.10
    0.5%
    314
    +0.10
    0.5%
    28
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.26
    160
    +0.10
    0.16
    314
    +0.09
    -0.04
    Negative Logits
     srfAttach
    -0.66
     guiActiveUn
    -0.65
     rhy
    -0.63
    VALUE
    -0.59
    ById
    -0.57
     heterogeneity
    -0.56
     Advocate
    -0.55
    Cause
    -0.55
     superst
    -0.54
     discrep
    -0.54
    POSITIVE LOGITS
    nz
    0.90
    merce
    0.87
    uk
    0.86
    ortment
    0.74
    lisher
    0.71
    jp
    0.70
    mx
    0.67
    cil
    0.65
    monary
    0.65
    lear
    0.65
    Activations Density 6.245%

    No Known Activations