© 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. 512
    Prev
    Next
    INDEX
    Explanations

    results or outcomes of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate consequences or outcomes

    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
    tsky
    -0.63
     spaced
    -0.58
     Talking
    -0.55
     Chili
    -0.54
     Neigh
    -0.52
     Neighbor
    -0.52
     Centauri
    -0.51
     craw
    -0.50
    edo
    -0.49
     reckoned
    -0.49
    POSITIVE LOGITS
     in
    0.85
    antly
    0.83
    aneously
    0.77
    igate
    0.75
    inally
    0.73
    inct
    0.67
     from
    0.67
    iate
    0.64
    âĹ¼
    0.64
    inals
    0.63
    Activations Density 0.057%

    No Known Activations