© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    parts in text where there are multiple periods appearing in sequence

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or other punctuation indicating a pause or omission in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krug
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    ously
    -0.70
    uers
    -0.69
    olas
    -0.68
     slope
    -0.66
     slopes
    -0.65
     Galile
    -0.64
    iosyncr
    -0.63
    govtrack
    -0.62
    POSITIVE LOGITS
    etc
    1.01
    Ħ¢
    0.84
    please
    0.83
    walking
    0.83
    where
    0.81
    WOR
    0.75
    Pa
    0.75
    err
    0.75
    MORE
    0.75
    which
    0.74
    Activations Density 0.019%

    No Known Activations