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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5725
    Prev
    Next
    INDEX
    Explanations

    the name "Hughes" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Hughes"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickr
    -0.89
    oker
    -0.80
    cape
    -0.80
    onym
    -0.78
    ographer
    -0.73
    ctica
    -0.73
    ographers
    -0.69
    âĹ¼
    -0.69
    ograph
    -0.69
    apping
    -0.68
    POSITIVE LOGITS
    glers
    1.02
     Chavez
    0.81
    Hunt
    0.75
    ged
    0.74
    aneers
    0.74
    mong
    0.72
    asus
    0.68
    inx
    0.66
    hett
    0.64
    master
    0.63
    Activations Density 0.061%

    No Known Activations