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

    Neuronpedia

    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. 8-RES-JB
    11. 19279
    Prev
    Next
    INDEX
    Explanations

    names and details related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    information related to legal and criminal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optim
    -0.83
    phies
    -0.74
    20439
    -0.74
     Sturgeon
    -0.73
     optim
    -0.73
    Brexit
    -0.73
     nostalg
    -0.71
    isSpecialOrderable
    -0.69
    1080
    -0.68
    ¨
    -0.68
    POSITIVE LOGITS
     arrested
    1.31
     sentenced
    1.30
     pleaded
    1.29
     convicted
    1.27
     arra
    1.21
     pled
    1.18
     unlawfully
    1.14
     allegedly
    1.13
     indicted
    1.12
     jailed
    1.12
    Activations Density 0.402%

    No Known Activations