© 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. 17285
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or activities performed by people

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate connection or addition

    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
    aceae
    -0.68
    ledged
    -0.62
    ISE
    -0.61
    ?????-
    -0.61
    elist
    -0.60
    thora
    -0.60
    rued
    -0.60
    ptoms
    -0.57
     Liberties
    -0.56
    pps
    -0.55
    POSITIVE LOGITS
     repairing
    1.60
     distributing
    1.55
     executing
    1.51
     administering
    1.49
     analyzing
    1.49
     modifying
    1.49
     photograp
    1.48
     exchanging
    1.48
     manipulating
    1.48
     arranging
    1.47
    Activations Density 0.392%

    No Known Activations