© 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. 7-RES-JB
    11. 19513
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific locations, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    geographical references and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.63
    enegger
    -0.53
    */(
    -0.51
    ãĥīãĥ©
    -0.51
    anyahu
    -0.51
    hement
    -0.50
     Niet
    -0.49
    jri
    -0.49
    milo
    -0.48
    alion
    -0.48
    POSITIVE LOGITS
     lately
    0.51
    's
    0.49
     besides
    0.48
     nowadays
    0.48
    ®
    0.46
    ÃŃs
    0.45
    âĦ¢
    0.44
     COUNTY
    0.44
     fandom
    0.42
    .
    0.42
    Activations Density 1.035%

    No Known Activations