© 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. 9-RES-JB
    11. 18634
    Prev
    Next
    INDEX
    Explanations

    words related to specific objects or concepts, such as arrays, dogs, guns, tunnels, cars, vaccines, massacres, horses, tablets, eggs, computers, sidewalks, trees, and men/jobs

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various societal issues and topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Submission
    -0.65
    osi
    -0.64
     Candidate
    -0.64
     Heist
    -0.63
     Spartan
    -0.63
     VID
    -0.62
    atorium
    -0.59
    MENTS
    -0.59
     submission
    -0.58
     Serbian
    -0.58
    POSITIVE LOGITS
    paces
    1.33
    chool
    1.21
    ynthesis
    1.19
    pace
    1.17
    poons
    1.14
    hip
    1.14
    creen
    1.12
    hift
    1.11
    hips
    1.10
    mith
    1.07
    Activations Density 0.499%

    No Known Activations