© 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. 10-RES-JB
    11. 20319
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names with two words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consolid
    -0.63
     disadvantaged
    -0.62
     deleg
    -0.61
     otherwise
    -0.61
     theirs
    -0.60
     realistically
    -0.59
     economically
    -0.59
     supplemented
    -0.59
     reserv
    -0.59
     subdiv
    -0.58
    POSITIVE LOGITS
     Revenge
    1.06
    kaya
    1.01
     Daughter
    0.97
    wered
    0.94
    niper
    0.93
     Choice
    0.92
    arah
    0.92
    ullivan
    0.90
     Latest
    0.89
    keleton
    0.88
    Activations Density 0.133%

    No Known Activations