© 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. 9485
    Prev
    Next
    INDEX
    Explanations

    references to journalistic sources and quotes from news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic or media-related production and commentary

    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
    Copyright
    -0.60
     Kavanaugh
    -0.55
    heid
    -0.55
     Guantanamo
    -0.54
    20439
    -0.54
    hya
    -0.54
    INTON
    -0.52
    Rated
    -0.52
    )--
    -0.52
    UTERS
    -0.51
    POSITIVE LOGITS
    vertisement
    0.62
    ccording
    0.60
    uitous
    0.55
    uilt
    0.55
    untled
    0.55
    ilst
    0.50
    çīĪ
    0.50
    oaded
    0.50
    anwhile
    0.49
    irtual
    0.49
    Activations Density 1.870%

    No Known Activations