© 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. 11484
    Prev
    Next
    INDEX
    Explanations

    places or incidents involving physical impact or damage

    oai_token-act-pair · gpt-3.5-turbo

    references to accidents, conflicts, and the consequences of actions

    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
    ":"/
    -0.69
    Rated
    -0.61
     endif
    -0.57
    Els
    -0.56
    NOW
    -0.56
    Fight
    -0.56
     cx
    -0.55
    mor
    -0.55
     \'
    -0.55
     rightful
    -0.55
    POSITIVE LOGITS
     there
    0.88
     we
    0.76
    ,
    0.73
     pandemonium
    0.68
     they
    0.67
    there
    0.65
     lies
    0.62
    hea
    0.61
     Sabha
    0.54
    orthern
    0.53
    Activations Density 0.862%

    No Known Activations