© 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. 9-RES-JB
    11. 2399
    Prev
    Next
    INDEX
    Explanations

    adjectives related to speed or pace

    oai_token-act-pair · gpt-3.5-turbo

    references to small, fictional creatures, particularly those resembling Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.83
    çīĪ
    -0.76
    illon
    -0.73
    amara
    -0.72
    merce
    -0.70
    ITION
    -0.69
    osate
    -0.68
    IDA
    -0.68
    mberg
    -0.67
     Aires
    -0.67
    POSITIVE LOGITS
    downs
    1.20
     cooker
    1.18
    poke
    1.18
     paced
    1.13
    est
    1.06
    idious
    0.95
     pace
    0.91
    down
    0.90
     speeds
    0.87
     twitch
    0.86
    Activations Density 0.029%

    No Known Activations