© 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. 1-RES-JB
    6. 18778
    Prev
    Next
    INDEX
    Explanations

    phrases related to common occurrences or generalizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate commonness or habitual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kob
    -0.69
     Chains
    -0.66
    hole
    -0.66
     Kardashian
    -0.66
    holes
    -0.65
     Purpose
    -0.65
     Sheikh
    -0.64
     Razor
    -0.62
     Mark
    -0.61
    plates
    -0.61
    POSITIVE LOGITS
    entimes
    1.02
    pmwiki
    0.98
     exha
    0.90
     occas
    0.86
     compr
    0.80
    wcs
    0.80
    »Ĵ
    0.79
    ©¶æ
    0.79
     assum
    0.76
     assumed
    0.75
    Activations Density 0.011%

    No Known Activations