© 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. 10-RES-JB
    11. 10196
    Prev
    Next
    INDEX
    Explanations

    the name or part of the name "ane" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Cane" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -0.82
    s
    -0.79
    spring
    -0.71
    enance
    -0.70
    porary
    -0.69
     Carbuncle
    -0.69
    stones
    -0.68
    ournal
    -0.68
     tack
    -0.67
    minded
    -0.67
    POSITIVE LOGITS
    gas
    0.91
    IRO
    0.86
    venue
    0.84
    hyde
    0.84
    agle
    0.82
    cki
    0.81
    anu
    0.79
    vich
    0.78
    gger
    0.77
    zie
    0.77
    Activations Density 0.058%

    No Known Activations