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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7234
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those associated with commentary or opinions

    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
    graded
    -0.79
    words
    -0.78
    grading
    -0.78
    eat
    -0.74
    etermined
    -0.73
    ocaust
    -0.72
    usable
    -0.71
    jong
    -0.71
     spare
    -0.70
    ournal
    -0.70
    POSITIVE LOGITS
     Weaver
    1.24
    lings
    0.72
    ¯
    0.68
     Remastered
    0.67
     Ashe
    0.67
    gren
    0.67
    eers
    0.66
    ILA
    0.65
     Widow
    0.64
     Firefly
    0.64
    Activations Density 0.007%

    No Known Activations