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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4-RES-JB
    6. 6904
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Japanese culture and individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of characters, creators, or notable figures in the context of film and animation

    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
    adelphia
    -0.69
     trooper
    -0.68
     Lyme
    -0.68
     Pyth
    -0.66
    ttes
    -0.65
     troopers
    -0.64
    roads
    -0.63
    ophy
    -0.63
    beat
    -0.60
    course
    -0.60
    POSITIVE LOGITS
     Shogun
    1.23
    ichi
    1.10
    amoto
    1.05
    azaki
    1.04
    ihara
    1.03
     Yosh
    1.02
    ishi
    1.00
    oka
    1.00
    jin
    0.98
    ç·
    0.95
    Activations Density 0.053%

    No Known Activations