© 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. 10-RES-JB
    11. 16506
    Prev
    Next
    INDEX
    Explanations

    mentions of the filmmaker "Kojima"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Wojak" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ples
    -0.66
    rade
    -0.64
     bleach
    -0.64
     Dominion
    -0.64
    esville
    -0.63
    mingham
    -0.60
    raped
    -0.60
    idy
    -0.59
     Solitaire
    -0.59
    pled
    -0.58
    POSITIVE LOGITS
    ansky
    0.80
    owski
    0.77
    ÅĤ
    0.71
    jan
    0.71
    cies
    0.70
    inski
    0.68
    anski
    0.68
    zl
    0.66
    zzi
    0.64
    owicz
    0.63
    Activations Density 0.066%

    No Known Activations