© 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. 10-RES-JB
    11. 24531
    Prev
    Next
    INDEX
    Explanations

    words related to specific named entities, particularly names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    names associated with individuals in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogy
    -0.75
    ãĥł
    -0.73
    ãĥ¼ãĤ¯
    -0.69
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    DAQ
    -0.66
    ument
    -0.65
     Rhino
    -0.63
    uments
    -0.62
    heses
    -0.62
    ngth
    -0.62
    POSITIVE LOGITS
    ocate
    0.82
    enegger
    0.82
    merga
    0.78
    isc
    0.77
    asar
    0.74
    entry
    0.74
    ifter
    0.74
    vez
    0.73
    awar
    0.73
    unctions
    0.71
    Activations Density 0.074%

    No Known Activations