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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5009
    Prev
    Next
    INDEX
    Explanations

    information related to urban areas and city life

    oai_token-act-pair · gpt-3.5-turbo

    references to various contemporary cultural and political phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ependent
    -0.66
    yss
    -0.62
    abolic
    -0.58
    mediate
    -0.56
    pard
    -0.55
     Hort
    -0.54
    local
    -0.53
     Insight
    -0.53
     COUNTY
    -0.52
    cipled
    -0.52
    POSITIVE LOGITS
    anooga
    0.73
    .).
    0.70
    *.
    0.70
    >.
    0.67
     notwithstanding
    0.65
    ?).
    0.63
    }.
    0.63
     attRot
    0.62
    ="/
    0.61
     respectively
    0.61
    Activations Density 1.157%

    No Known Activations