© 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. 18739
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or decision making

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions related to causality and consequences

    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
    ector
    -0.82
    allery
    -0.82
    atform
    -0.76
    INAL
    -0.76
    vantage
    -0.74
    eatures
    -0.72
    uid
    -0.70
    ributed
    -0.70
    aic
    -0.69
    ELD
    -0.67
    POSITIVE LOGITS
     hating
    1.54
     worrying
    1.48
     forgetting
    1.45
     messing
    1.40
     pretending
    1.39
     thinking
    1.36
     wanting
    1.35
     liking
    1.35
     wasting
    1.35
     wondering
    1.33
    Activations Density 0.449%

    No Known Activations