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. 0-RES-JB
    6. 21307
    Prev
    Next
    INDEX
    Explanations

    references to phonographs or gramophones

    oai_token-act-pair · gpt-3.5-turbo

    words related to phonographs and specific locations or demographics connected to Brunswick

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gors
    -0.79
     hiber
    -0.72
    LV
    -0.69
     Cul
    -0.66
     Ily
    -0.66
     fir
    -0.66
     Fit
    -0.66
     Bucc
    -0.65
    outs
    -0.64
     IRS
    -0.63
    POSITIVE LOGITS
    ophone
    3.13
    ophon
    2.59
     Brunswick
    1.50
    swick
    1.26
     Alto
    1.11
    arine
    1.09
    itory
    0.99
    ça
    0.99
    ienne
    0.96
    rador
    0.94
    Activations Density 0.057%

    No Known Activations