© 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. 9-RES-JB
    11. 18112
    Prev
    Next
    INDEX
    Explanations

    sequences that involve physical movements or actions

    oai_token-act-pair · gpt-3.5-turbo

    key actions or processes aimed at rescue or recovery efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     à¨
    -0.56
     hindsight
    -0.56
    à©
    -0.55
     overest
    -0.52
     Analog
    -0.51
     Subtle
    -0.51
     comprom
    -0.50
    theless
    -0.50
     repud
    -0.50
     Moz
    -0.50
    POSITIVE LOGITS
     safely
    0.91
    ().
    0.84
    .
    0.77
    .;
    0.73
    ãĢĤ
    0.72
    UTF
    0.71
    .#
    0.68
    %.
    0.67
    $.
    0.66
    .[
    0.64
    Activations Density 1.119%

    No Known Activations