© 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. 7139
    Prev
    Next
    INDEX
    Explanations

    terms related to policies, actions, or outcomes

    oai_token-act-pair · gpt-3.5-turbo
    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
    è¦
    -0.78
     Entered
    -0.69
    icipated
    -0.67
     Cosponsors
    -0.63
    awaru
    -0.62
    76561
    -0.62
     Joined
    -0.62
    utm
    -0.61
    ijah
    -0.61
    started
    -0.61
    POSITIVE LOGITS
     obsolete
    1.26
     easier
    1.20
     safer
    1.14
     seem
    1.10
     redundant
    1.09
     impossible
    1.06
     irrelevant
    1.03
     attractive
    1.01
     unus
    1.00
     harder
    0.99
    Activations Density 0.134%

    No Known Activations