© 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. 10003
    Prev
    Next
    INDEX
    Explanations

    numerals with space in between them

    oai_token-act-pair · gpt-3.5-turbo

    questions and reflections on past events

    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
     conduc
    -0.76
     maximizing
    -0.73
     sacrific
    -0.69
    uties
    -0.68
     yielding
    -0.65
     subdu
    -0.65
     maximize
    -0.64
    advant
    -0.64
    icient
    -0.63
    endish
    -0.63
    POSITIVE LOGITS
    terday
    1.42
     happened
    1.03
     yesterday
    1.03
    Yesterday
    0.98
    cember
    0.97
     hadn
    0.95
     forgot
    0.94
    ometime
    0.93
     ago
    0.93
     hindsight
    0.91
    Activations Density 0.592%

    No Known Activations