© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to finishing or completion

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
    Ul
    -0.71
     ®
    -0.69
     Rud
    -0.64
     rabbi
    -0.63
     slope
    -0.63
     rabbit
    -0.63
     rabbits
    -0.63
    Sham
    -0.63
    aeus
    -0.62
     Wonderland
    -0.62
    POSITIVE LOGITS
    nard
    2.25
     finishes
    1.84
     revital
    1.56
    jas
    1.33
     Pens
    1.06
     dign
    0.99
     rejuven
    0.97
    gres
    0.96
     Amar
    0.95
     Prescott
    0.93
    Activations Density 0.045%

    No Known Activations