© 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 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. 3845
    Prev
    Next
    INDEX
    Explanations

    words related to different types or categories

    oai_token-act-pair · gpt-3.5-turbo

    terms that specify different types or categories of concepts and entities

    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
    )</
    -0.76
     shores
    -0.73
     Ruins
    -0.63
    txt
    -0.63
    oppers
    -0.63
    CHAT
    -0.62
    anwhile
    -0.62
     HOU
    -0.60
     Jah
    -0.59
    %);
    -0.59
    POSITIVE LOGITS
     guiActiveUnfocused
    0.90
     imaginable
    0.89
    iform
    0.66
     shenan
    0.65
    manship
    0.64
    ivalry
    0.63
     populism
    0.63
     intervention
    0.63
    anship
    0.61
     arrangement
    0.60
    Activations Density 0.286%

    No Known Activations