© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "actor" or "actress."

    oai_token-act-pair · gpt-3.5-turbo

    words related to functions and functional programming concepts

    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
    vag
    -0.72
    plates
    -0.69
    ggle
    -0.68
    fc
    -0.66
    dh
    -0.66
    lik
    -0.65
    IGH
    -0.63
    ¥ŀ
    -0.61
    nah
    -0.61
    TIT
    -0.61
    POSITIVE LOGITS
    ctor
    1.14
    ctors
    0.89
    ially
    0.85
    isy
    0.79
    女
    0.79
    ivari
    0.78
    iatrics
    0.78
    ial
    0.76
    hyde
    0.76
    iculture
    0.76
    Activations Density 0.021%

    No Known Activations