© 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. 4-RES-JB
    11. 361
    Prev
    Next
    INDEX
    Explanations

    mentions related to spacesuits and protective garments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "suit."

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

    No Comments

    Negative Logits
    mob
    -0.77
    birth
    -0.69
     ILCS
    -0.69
    480
    -0.68
    ILY
    -0.66
    20439
    -0.63
    088
    -0.60
    deal
    -0.60
     NCT
    -0.59
    951
    -0.59
    POSITIVE LOGITS
    uit
    1.09
    eers
    0.99
    eer
    0.97
    eering
    0.87
    uits
    0.83
    arist
    0.78
    eness
    0.75
    ously
    0.73
    oise
    0.72
    rador
    0.72
    Activations Density 0.010%

    No Known Activations