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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3258
    Prev
    Next
    INDEX
    Explanations

    numbers and specific details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant events or legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.72
    Newsletter
    -0.71
    wcs
    -0.64
    foreseen
    -0.64
    establishment
    -0.63
    requisite
    -0.63
    ifference
    -0.63
     :=
    -0.62
    ":[{"
    -0.61
    enance
    -0.61
    POSITIVE LOGITS
    !).
    1.68
    !)
    1.67
    ?).
    1.62
    !),
    1.58
    ?)
    1.57
    *)
    1.55
    )</
    1.48
    ?),
    1.45
    ).
    1.43
    )."
    1.39
    Activations Density 0.462%

    No Known Activations