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

    Neuronpedia

    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. 4-RES-JB
    11. 22216
    Prev
    Next
    INDEX
    Explanations

    mentions of being inducted or honored in a hall of fame

    oai_token-act-pair · gpt-3.5-turbo

    references to various "Halls of Fame."

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

    No Comments

    Negative Logits
    resp
    -0.77
    owicz
    -0.67
    ihad
    -0.66
     Anon
    -0.65
    nian
    -0.65
     Gork
    -0.64
    nia
    -0.64
    apest
    -0.63
     PLAN
    -0.63
    selves
    -0.63
    POSITIVE LOGITS
     Fame
    1.21
    rities
    0.88
     induction
    0.82
     honors
    0.81
     induct
    0.78
    brance
    0.77
     honored
    0.76
     Bowl
    0.75
    naire
    0.75
     fame
    0.74
    Activations Density 0.007%

    No Known Activations