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. 40075
    Prev
    Next
    INDEX
    Explanations

    mentions related to food contamination or environmental impacts on local food industries

    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
    583
    +0.06
    0.5%
    393
    +0.06
    0.5%
    712
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.17
    578
    +0.06
    0.04
    522
    +0.06
    0.07
    Negative Logits
    velop
    -0.43
    onent
    -0.38
    oak
    -0.37
    igraph
    -0.36
    UME
    -0.34
    erers
    -0.34
    agos
    -0.33
    cember
    -0.32
    son
    -0.32
    inances
    -0.31
    POSITIVE LOGITS
     gonna
    0.58
     gotta
    0.58
     happened
    0.53
     been
    0.50
     got
    0.49
    pace
    0.47
     gotten
    0.46
     happening
    0.44
     transpired
    0.42
     done
    0.41
    Activations Density 5.299%

    No Known Activations