© 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. 18738
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to seasons, time, and specific scales of measurement

    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
    pires
    -0.59
    dimension
    -0.57
    ãĥĻ
    -0.56
    ãĥĥãĥĪ
    -0.53
    ãĥ¼ãĥĨãĤ£
    -0.52
    \":
    -0.52
    pired
    -0.49
    ãĥŀ
    -0.48
    ãģĹ
    -0.47
    ãĤª
    -0.47
    POSITIVE LOGITS
     because
    1.04
     though
    0.98
    ;
    0.98
     but
    0.94
     whereas
    0.94
     although
    0.93
    .;
    0.87
     however
    0.84
     unless
    0.81
    .
    0.76
    Activations Density 1.574%

    No Known Activations