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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 21461
    Prev
    Next
    INDEX
    Explanations

    phrases related to functioning actions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    closing punctuation marks, particularly parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":[{"
    -0.51
     Reverend
    -0.46
     absolutely
    -0.41
     ambassadors
    -0.41
     insider
    -0.40
    achu
    -0.39
     Original
    -0.39
     ambassador
    -0.38
     investig
    -0.38
    Newsletter
    -0.38
    POSITIVE LOGITS
    ).
    3.06
    )."
    2.98
    ?).
    2.90
    .).
    2.86
    !).
    2.76
    ').
    2.74
    ).[
    2.74
    )).
    2.69
    )!
    2.54
     ).
    2.54
    Activations Density 0.055%

    No Known Activations