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. 1-RES-JB
    6. 6213
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term, "ush"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring 'ush' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stake
    -0.73
    İĭ
    -0.71
     stakes
    -0.68
     rele
    -0.65
     permit
    -0.64
     substituted
    -0.63
     occup
    -0.63
    elong
    -0.62
     permitting
    -0.62
    psey
    -0.62
    POSITIVE LOGITS
    ush
    1.33
    ivas
    0.82
     Leopard
    0.79
    oku
    0.79
    ORTS
    0.77
    lings
    0.76
    adows
    0.75
    ank
    0.75
    adow
    0.75
    trap
    0.74
    Activations Density 0.005%

    No Known Activations