Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20378
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms, potentially related to celebrities or public figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Radiant
    -1.01
     Rend
    -0.98
     Tid
    -0.96
     Trin
    -0.90
     Tud
    -0.90
     Nost
    -0.89
    NT
    -0.88
     Timbers
    -0.86
     Rat
    -0.84
     Nit
    -0.83
    POSITIVE LOGITS
    au
    1.30
    aul
    1.14
     Lau
    1.03
    Marie
    0.97
     HEL
    0.94
     Kau
    0.93
     Kaufman
    0.93
     Mau
    0.92
    aus
    0.90
    AU
    0.90
    Activations Density 0.603%

    No Known Activations