© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 1
    Prev
    Next
    INDEX
    Explanations

    words related to searching, scouring, or investigating a specific area or topic

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and variations of "our."

    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
    Origin
    -0.64
    RN
    -0.64
    ersion
    -0.63
    ohn
    -0.63
     Reloaded
    -0.61
     reaction
    -0.61
    actly
    -0.61
    manship
    -0.61
    attach
    -0.60
     sworn
    -0.60
    POSITIVE LOGITS
    ours
    1.04
    neau
    0.82
    ouring
    0.80
    oured
    0.78
    raine
    0.73
    hower
    0.73
    wikipedia
    0.72
    ¯¯¯¯¯¯¯¯
    0.72
     Lys
    0.71
    rain
    0.70
    Activations Density 0.019%

    No Known Activations