© 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. 2-RES-JB
    11. 12690
    Prev
    Next
    INDEX
    Explanations

    numerical figures related to various statistics or 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actic
    -0.75
    prototype
    -0.73
    folk
    -0.72
    gart
    -0.72
    lied
    -0.71
    н
    -0.70
    odore
    -0.69
    alg
    -0.67
    furt
    -0.67
    ategic
    -0.66
    POSITIVE LOGITS
     ILCS
    0.85
     calories
    0.74
     pounds
    0.67
    °
    0.66
     MHz
    0.66
     lbs
    0.65
     pages
    0.65
     kcal
    0.63
     degrees
    0.62
     pound
    0.61
    Activations Density 0.053%

    No Known Activations