© 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. 8-RES-JB
    11. 22495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with law enforcement and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assembly
    -0.70
     Breakfast
    -0.68
     surn
    -0.65
     Islands
    -0.65
    Scroll
    -0.63
    onics
    -0.63
    bian
    -0.63
    anka
    -0.63
     Cree
    -0.62
    ukemia
    -0.61
    POSITIVE LOGITS
     unconsciously
    1.16
     subconscious
    1.14
     implicitly
    0.96
     passively
    0.94
     instinctively
    0.90
     thereby
    0.89
     infer
    0.87
     knowing
    0.85
     subtly
    0.85
     perce
    0.85
    Activations Density 1.146%

    No Known Activations