© 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. 11-RES-JB
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or abundance of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a lot" indicating abundance or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESCO
    -0.60
    ħĭ
    -0.57
    edIn
    -0.55
    xon
    -0.55
    Materials
    -0.54
    terson
    -0.53
    yx
    -0.53
    furt
    -0.52
    inary
    -0.51
    acia
    -0.51
    POSITIVE LOGITS
     of
    1.09
     more
    0.84
     riding
    0.82
     happening
    0.79
     less
    0.75
     fewer
    0.75
     OF
    0.73
     thereof
    0.70
     easier
    0.70
     Of
    0.70
    Activations Density 0.051%

    No Known Activations