© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20701
    Prev
    Next
    INDEX
    Explanations

    the name "Blake"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Blake."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demand
    -0.71
    egal
    -0.71
    ocard
    -0.70
    ktop
    -0.69
     plur
    -0.67
    ãĥķãĤ©
    -0.66
     srfAttach
    -0.65
    nih
    -0.65
    swing
    -0.63
     horm
    -0.63
    POSITIVE LOGITS
    pedia
    0.87
    apult
    0.86
    mint
    0.80
    querque
    0.78
    halla
    0.77
    wick
    0.77
    fighting
    0.76
    osure
    0.76
    more
    0.75
    rette
    0.75
    Activations Density 0.026%

    No Known Activations