© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    words related to research studies and scientific findings

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons and contrasts in various contexts

    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
    bucks
    -0.80
    icken
    -0.77
    votes
    -0.76
    bolt
    -0.76
    @
    -0.67
    Fax
    -0.67
    mails
    -0.65
    Channel
    -0.65
    rss
    -0.63
     Gazette
    -0.63
    POSITIVE LOGITS
     tended
    0.98
     relied
    0.88
     struggled
    0.88
     emulate
    0.88
     preceded
    0.84
     gimm
    0.83
     fal
    0.83
     rely
    0.82
     empires
    0.79
     tend
    0.79
    Activations Density 0.488%

    No Known Activations