© 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. 11232
    Prev
    Next
    INDEX
    Explanations

    fractions represented by the "frac" formatting

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and terms related to fractions and compatibility

    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
    istically
    -0.82
    ike
    -0.81
    getic
    -0.79
    fman
    -0.75
    idth
    -0.74
    omore
    -0.73
    bley
    -0.72
    gradation
    -0.71
    iller
    -0.71
    izons
    -0.70
    POSITIVE LOGITS
    burg
    0.70
    ãģŁ
    0.70
    ãģ¦
    0.69
    TERN
    0.69
    mented
    0.69
    shaw
    0.67
    ãĥ¼ãĤ¯
    0.64
    ounded
    0.63
     Concord
    0.63
     tracts
    0.62
    Activations Density 0.036%

    No Known Activations