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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24570
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "but" indicating contrast or exception

    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
    ahime
    -0.81
    VERTISEMENT
    -0.70
    itures
    -0.66
    nown
    -0.65
    iliary
    -0.65
    essing
    -0.63
     Offline
    -0.63
    velt
    -0.61
    iley
    -0.60
    ccording
    -0.60
    POSITIVE LOGITS
    ieu
    0.77
     praise
    0.73
    pure
    0.71
    tons
    0.70
    hin
    0.69
    forth
    0.67
    èª
    0.66
     accepts
    0.66
    che
    0.65
    hig
    0.63
    Activations Density 0.035%

    No Known Activations