© 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. 2732
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Carmichael"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Carm" and variations of it within the text

    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
    IS
    -0.69
    zai
    -0.68
    fts
    -0.66
    edition
    -0.66
     RUN
    -0.65
     SEAL
    -0.64
    igrate
    -0.63
    Fly
    -0.63
    Entry
    -0.62
    fly
    -0.61
    POSITIVE LOGITS
     Carm
    4.05
     Galile
    1.56
     Amar
    1.17
     Alam
    1.12
     Pist
    1.09
     Romero
    1.02
     Cind
    1.01
     Dw
    1.00
     Sebast
    0.98
     Cort
    0.98
    Activations Density 0.017%

    No Known Activations