© 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. 9-RES-JB
    11. 18258
    Prev
    Next
    INDEX
    Explanations

    references to specific experiments or technical procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military operations or strategic approaches

    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
    hower
    -0.91
    KEN
    -0.85
    KING
    -0.79
    oÄŁan
    -0.78
    ipeg
    -0.78
     Shake
    -0.71
    WIND
    -0.70
     GOODMAN
    -0.70
    RAY
    -0.70
    MH
    -0.69
    POSITIVE LOGITS
    atus
    1.31
    orum
    1.31
    ensis
    1.29
    inis
    1.20
    anus
    1.16
    iae
    1.15
    arius
    1.15
    ibus
    1.13
    ius
    1.13
    orem
    1.11
    Activations Density 0.548%

    No Known Activations