© 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. 1-RES-JB
    11. 20109
    Prev
    Next
    INDEX
    Explanations

    female political figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "woman" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asio
    -0.78
    ollow
    -0.71
    UFF
    -0.66
    omer
    -0.64
     decay
    -0.63
    vez
    -0.63
    ollo
    -0.62
    aze
    -0.61
    akespe
    -0.61
    ral
    -0.60
    POSITIVE LOGITS
    woman
    1.24
    士
    0.87
    women
    0.85
    uscript
    0.81
    Woman
    0.80
    puter
    0.80
    hood
    0.78
     Gaga
    0.76
    gdala
    0.76
    theless
    0.76
    Activations Density 0.009%

    No Known Activations