© 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. 4-RES-JB
    11. 20743
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to personal names

    oai_token-act-pair · gpt-3.5-turbo

    references to titles or ranks associated with individuals or entities

    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
    xon
    -0.85
    Hack
    -0.76
    hya
    -0.76
    berman
    -0.72
    mble
    -0.72
    hn
    -0.68
    gel
    -0.64
    ADRA
    -0.63
    ĸļ
    -0.61
    plet
    -0.61
    POSITIVE LOGITS
    awks
    1.07
    awk
    1.06
    ttp
    1.05
    orse
    0.84
    mares
    0.84
    ouses
    0.82
    ighth
    0.81
    azer
    0.78
    unction
    0.77
    olly
    0.77
    Activations Density 0.019%

    No Known Activations