© 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. 3-RES-JB
    11. 15775
    Prev
    Next
    INDEX
    Explanations

    phrases referring to different scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" indicating clauses or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.70
    Problem
    -0.70
    et
    -0.68
    ben
    -0.68
    hat
    -0.68
    FN
    -0.68
    Bug
    -0.67
    let
    -0.66
    ctor
    -0.62
     Tracker
    -0.60
    POSITIVE LOGITS
    soever
    0.95
    xual
    0.91
    ĸļ
    0.83
    ãĥ¯ãĥ³
    0.73
    akespeare
    0.67
    luaj
    0.66
    ispers
    0.64
    ãĥĢ
    0.63
    andom
    0.63
    ãĤ½
    0.62
    Activations Density 0.042%

    No Known Activations