© 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. 11-RES-JB
    11. 569
    Prev
    Next
    INDEX
    Explanations

    titles or positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles within organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zan
    -0.66
    izoph
    -0.59
    ãĥĥãĥī
    -0.58
    MAT
    -0.56
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.54
    entimes
    -0.54
    Stre
    -0.54
    Reward
    -0.54
    rescent
    -0.53
    mop
    -0.53
    POSITIVE LOGITS
     for
    1.08
     of
    1.05
     belonging
    0.77
     behind
    0.76
     at
    0.76
     thereof
    0.76
    for
    0.75
     aboard
    0.71
     overseeing
    0.69
    behind
    0.69
    Activations Density 0.637%

    No Known Activations