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. 7-RES-JB
    6. 23256
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or commonality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or regularity of occurrences

    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
    atur
    -0.91
    itivity
    -0.86
    ves
    -0.82
    uble
    -0.80
    atures
    -0.80
    ibility
    -0.78
    own
    -0.78
    idates
    -0.76
    itives
    -0.76
    leground
    -0.73
    POSITIVE LOGITS
     excluding
    1.06
     implying
    1.01
     preferring
    0.96
     indicating
    0.91
     numbering
    0.91
     suggesting
    0.90
     culminating
    0.89
     skipping
    0.88
     consisting
    0.88
     conclud
    0.88
    Activations Density 0.146%

    No Known Activations