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. 5-RES-JB
    6. 15994
    Prev
    Next
    INDEX
    Explanations

    contradictions or opposing statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "yet" indicating contrast or concession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rities
    -0.77
    edu
    -0.76
    tein
    -0.70
    ancial
    -0.68
    gang
    -0.66
    ussions
    -0.63
    Times
    -0.63
    Chicken
    -0.63
    puters
    -0.62
    cases
    -0.62
    POSITIVE LOGITS
     somehow
    0.97
     mirac
    0.78
     behold
    0.78
     inexpl
    0.74
     strangely
    0.73
    heric
    0.73
    tons
    0.71
    chart
    0.69
     somew
    0.69
     again
    0.68
    Activations Density 0.024%

    No Known Activations