© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    references to news media sources

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources

    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
    wcs
    -0.75
    ppings
    -0.71
    isable
    -0.70
    ause
    -0.68
    venge
    -0.68
    vol
    -0.66
    BuyableInstoreAndOnline
    -0.64
     dunno
    -0.63
    animate
    -0.63
    ¯¯
    -0.62
    POSITIVE LOGITS
    letters
    1.00
     Anch
    0.92
    radio
    0.88
     anchor
    0.87
    Radio
    0.84
     correspondent
    0.82
    ource
    0.77
    Asia
    0.76
     Coverage
    0.75
     anchors
    0.75
    Activations Density 0.027%

    No Known Activations