© 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. 0-RES-JB
    11. 16388
    Prev
    Next
    INDEX
    Explanations

    number sequences likely representing unique identifiers or codes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urations
    -0.77
    ãĤ£
    -0.71
     Seeking
    -0.71
     Helpful
    -0.66
    ventory
    -0.66
    naire
    -0.65
    yan
    -0.65
    ItemTracker
    -0.64
    ilde
    -0.64
    士
    -0.63
    POSITIVE LOGITS
    mson
    0.82
    acre
    0.77
    acter
    0.68
     Griffith
    0.67
    DH
    0.66
    RFC
    0.64
    agents
    0.63
     Pu
    0.61
     pathogens
    0.61
    iosyn
    0.60
    Activations Density 0.000%

    No Known Activations