© 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. 15259
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Hard"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Hard" in various contexts

    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
    uality
    -0.83
    umbn
    -0.76
    allery
    -0.75
    ript
    -0.73
    reon
    -0.70
    ĸļ
    -0.70
    idated
    -0.66
    uations
    -0.63
     Schumer
    -0.62
    entric
    -0.61
    POSITIVE LOGITS
    ened
    0.97
    ball
    0.94
    ness
    0.94
    ware
    0.94
    core
    0.89
    ening
    0.87
    iness
    0.86
    nesses
    0.82
    dri
    0.82
    hard
    0.82
    Activations Density 0.020%

    No Known Activations