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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 23510
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms related to a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific actions or events related to Pokémon games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Media
    -0.75
     Wrestling
    -0.71
     Basketball
    -0.70
     Notting
    -0.69
    lang
    -0.67
     Boxing
    -0.66
     Strat
    -0.66
     Conf
    -0.65
     Canary
    -0.64
    ospace
    -0.64
    POSITIVE LOGITS
    aned
    0.79
    enf
    0.75
    »Ĵ
    0.75
     waivers
    0.74
    bey
    0.72
     waiver
    0.72
    adra
    0.72
    roe
    0.70
    nect
    0.69
    tesy
    0.68
    Activations Density 0.000%

    No Known Activations