© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    terms related to human biology and anatomy

    oai_token-act-pair · gpt-3.5-turbo

    references to humans and human-related concepts

    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
    arella
    -0.84
    kick
    -0.77
    forth
    -0.72
    rent
    -0.71
    ère
    -0.70
    wark
    -0.69
    rypt
    -0.69
    raints
    -0.69
     Buckingham
    -0.68
    abb
    -0.68
    POSITIVE LOGITS
     beings
    1.19
    oids
    0.99
     readable
    0.95
     embryonic
    0.93
     civilization
    0.87
     civilisation
    0.82
    zee
    0.81
    itary
    0.78
    itar
    0.78
    ized
    0.77
    Activations Density 0.023%

    No Known Activations