© 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. 8-RES-JB
    11. 6377
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming languages and web development

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating tutorial or instructional content

    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
     Kills
    -0.68
     Canaveral
    -0.67
    Alert
    -0.67
    ['
    -0.63
     Guam
    -0.63
     Allies
    -0.62
    Fax
    -0.61
     Crimson
    -0.61
    ibles
    -0.60
     Gamble
    -0.60
    POSITIVE LOGITS
    escription
    0.88
     briefly
    0.86
     summarize
    0.85
    endix
    0.82
    resents
    0.82
    enda
    0.81
     propose
    0.79
     foc
    0.78
     analyse
    0.78
    Introdu
    0.77
    Activations Density 0.247%

    No Known Activations