© 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. 4-RES-JB
    11. 2897
    Prev
    Next
    INDEX
    Explanations

    financial or numerical values and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating addition or comparison between elements

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

    No Comments

    Negative Logits
    itiz
    -0.80
    ses
    -0.78
    enium
    -0.69
    ug
    -0.66
    ade
    -0.66
    ns
    -0.65
    onomy
    -0.64
    Fram
    -0.64
    MAS
    -0.64
    bugs
    -0.63
    POSITIVE LOGITS
     preferably
    0.73
     assuming
    0.71
    christ
    0.69
    arently
    0.68
     perhaps
    0.67
     namely
    0.67
     presumably
    0.67
     optionally
    0.65
     skipping
    0.64
     evidenced
    0.64
    Activations Density 0.432%

    No Known Activations