© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    references to laws or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation or laws

    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
    ricular
    -0.69
    asus
    -0.64
     Rubber
    -0.63
    xit
    -0.63
    ,,,,
    -0.63
     sqor
    -0.62
     Royale
    -0.61
    ixel
    -0.61
    emonic
    -0.61
     Voy
    -0.60
    POSITIVE LOGITS
     enforcement
    1.51
    lessness
    1.33
    suit
    1.30
    enforcement
    1.26
    breaking
    1.21
     Enforcement
    1.18
    suits
    1.18
     abiding
    1.17
    breakers
    1.16
    breaker
    1.13
    Activations Density 0.054%

    No Known Activations