© 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. 7-RES-JB
    11. 13406
    Prev
    Next
    INDEX
    Explanations

    words related to bill and money

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, brands, and titles, especially those related to cultural or literary contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.87
    ibles
    -0.84
    ierce
    -0.80
    eller
    -0.79
    ressive
    -0.79
    ially
    -0.75
    ression
    -0.72
    cean
    -0.71
    herty
    -0.71
    iled
    -0.71
    POSITIVE LOGITS
    laughter
    0.84
    phrase
    0.73
    pool
    0.73
    take
    0.73
    LOAD
    0.72
    dial
    0.71
    hao
    0.71
    bour
    0.71
     Mans
    0.66
    onest
    0.65
    Activations Density 0.072%

    No Known Activations