© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22286
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "all."

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity or universality in statements

    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
    ubi
    -0.67
     ASAP
    -0.61
    mire
    -0.59
     Loading
    -0.58
    aria
    -0.58
     Hold
    -0.58
    poke
    -0.57
    andra
    -0.57
    raped
    -0.57
    well
    -0.56
    POSITIVE LOGITS
     imaginable
    0.85
    士
    0.75
     tabl
    0.73
     conceivable
    0.71
    hyde
    0.69
    Downloadha
    0.64
    intestinal
    0.64
     aspirin
    0.63
     Occupations
    0.63
    chens
    0.62
    Activations Density 0.059%

    No Known Activations