Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4299
    Prev
    Next
    INDEX
    Explanations

    the name "Perez"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Perez."

    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
    gling
    -0.99
    roups
    -0.89
    bane
    -0.86
    atics
    -0.86
    itate
    -0.83
    creen
    -0.82
    wagen
    -0.82
    sis
    -0.81
    ences
    -0.78
    phis
    -0.78
    POSITIVE LOGITS
    ointed
    0.73
    9999
    0.66
    200000
    0.64
    ascal
    0.63
    Ò
    0.63
    ected
    0.63
    oses
    0.63
    agn
    0.62
    acks
    0.61
    onse
    0.60
    Activations Density 0.099%

    No Known Activations