© 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. 10-RES-JB
    11. 20349
    Prev
    Next
    INDEX
    Explanations

    words related to past actions or completed tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to academic or formal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eatures
    -0.58
    ghai
    -0.57
    quartered
    -0.53
     Sundays
    -0.52
    edIn
    -0.50
     hospitality
    -0.49
    rely
    -0.49
     pilgr
    -0.49
    ofi
    -0.48
     Saturdays
    -0.48
    POSITIVE LOGITS
    /,
    0.75
     (!
    0.73
    ;
    0.72
    .
    0.68
     haha
    0.67
     lol
    0.67
     :)
    0.66
    !:
    0.65
     ("
    0.63
     etc
    0.63
    Activations Density 1.186%

    No Known Activations