© 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. 9-RES-JB
    11. 9151
    Prev
    Next
    INDEX
    Explanations

    proper nouns or terms related to names or titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frog
    -0.60
    etheus
    -0.59
    ython
    -0.59
    omas
    -0.58
     HRC
    -0.57
    gdala
    -0.56
    ango
    -0.56
    atana
    -0.55
    hea
    -0.55
     stagnation
    -0.54
    POSITIVE LOGITS
     wont
    1.00
    pmwiki
    0.72
     ().
    0.70
    _.
    0.70
    phrase
    0.67
    ÑĮ
    0.66
     nowadays
    0.65
     attest
    0.63
    (),
    0.63
    displayText
    0.62
    Activations Density 0.185%

    No Known Activations