© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1861
    Prev
    Next
    INDEX
    Explanations

    statements indicating readiness or potential for specific actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness or potential for action

    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
    PLIED
    -0.74
     syndrome
    -0.59
    Neal
    -0.58
    isms
    -0.58
    illin
    -0.57
    tein
    -0.56
    DOS
    -0.56
    @#&
    -0.56
    ochet
    -0.56
    Kay
    -0.56
    POSITIVE LOGITS
     Parenthood
    0.84
    onite
    0.72
    º
    0.71
    gest
    0.69
     doomed
    0.66
    entious
    0.64
    igon
    0.63
    untarily
    0.63
    ĭ
    0.62
    atile
    0.62
    Activations Density 0.087%

    No Known Activations