© 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. 0-RES-JB
    11. 16370
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Powell."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Powell"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ice
    -0.70
     hail
    -0.69
     HA
    -0.66
     herpes
    -0.64
     solar
    -0.64
     armor
    -0.64
     Angels
    -0.63
     lifes
    -0.62
     heal
    -0.62
     healing
    -0.62
    POSITIVE LOGITS
     Powell
    4.20
    owell
    1.53
     Porter
    1.23
     Pryor
    1.19
     Mills
    1.18
     Blair
    1.17
     Patel
    1.14
     Dunham
    1.13
     Pound
    1.11
     Nicholson
    1.10
    Activations Density 0.019%

    No Known Activations