© 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. 4-RES-JB
    11. 14721
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences prompting action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "let's" followed by various actions or suggestions

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

    No Comments

    Negative Logits
    ELD
    -0.71
     Deaths
    -0.68
    rupted
    -0.65
     haun
    -0.64
    CLUD
    -0.62
     surrounds
    -0.62
    IED
    -0.61
     biod
    -0.61
    eur
    -0.59
    URI
    -0.59
    POSITIVE LOGITS
     gotta
    0.94
     gonna
    0.94
     suppose
    0.93
     got
    0.82
     assume
    0.77
     pretend
    0.76
     speculate
    0.76
    dule
    0.74
     suspend
    0.72
     move
    0.71
    Activations Density 0.019%

    No Known Activations