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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 8945
    Prev
    Next
    INDEX
    Explanations

    the name "Eric Holder"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Eric Holder

    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
    chrom
    -0.78
    igm
    -0.71
    eto
    -0.70
    urious
    -0.70
    elfth
    -0.64
    eele
    -0.63
    orthodox
    -0.63
    oster
    -0.62
     Typh
    -0.62
    okes
    -0.62
    POSITIVE LOGITS
     Holder
    0.97
    mann
    0.91
    stein
    0.89
    mans
    0.81
    maid
    0.76
    artz
    0.75
    holder
    0.74
    stack
    0.72
    ns
    0.72
    gren
    0.71
    Activations Density 0.016%

    No Known Activations