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

    Neuronpedia

    Jacobian LensNEW
    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. 2074
    Prev
    Next
    INDEX
    Explanations

    items with numbers or specific measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    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
    ĵĺ
    -0.66
     scissors
    -0.62
     contention
    -0.61
    ophon
    -0.59
     habit
    -0.59
    yss
    -0.59
    axy
    -0.59
     cue
    -0.59
     Bok
    -0.58
     hol
    -0.58
    POSITIVE LOGITS
    ãĥīãĥ©ãĤ´ãĥ³
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.82
    254
    0.76
    266
    0.73
    660
    0.73
    230
    0.70
    ãĥ¯ãĥ³
    0.70
    435
    0.70
    ãĥĻ
    0.69
    238
    0.69
    Activations Density 0.238%

    No Known Activations