© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    instances of the word "working on"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "working on"

    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
    ists
    -0.77
    zynski
    -0.70
    ennes
    -0.69
    ista
    -0.68
    emphasis
    -0.68
    lege
    -0.68
    YY
    -0.67
    warm
    -0.66
     hesitate
    -0.66
    vantage
    -0.65
    POSITIVE LOGITS
     behalf
    1.76
     improving
    1.16
     projects
    1.10
     developing
    1.00
     solving
    0.98
     implementing
    0.97
     integrating
    0.96
     figuring
    0.96
     constructing
    0.96
     adapting
    0.94
    Activations Density 0.143%

    No Known Activations