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. 7-RES-JB
    6. 12855
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, "Gul"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Gul

    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
     Wales
    -0.69
    acters
    -0.64
     Speedway
    -0.61
     Sacrament
    -0.60
     Covenant
    -0.60
     Welsh
    -0.60
     Universe
    -0.60
     division
    -0.59
     Granger
    -0.57
     Hots
    -0.57
    POSITIVE LOGITS
    mud
    1.02
    zeb
    0.96
    gur
    0.95
    pin
    0.92
    bling
    0.91
    zar
    0.91
    entle
    0.90
    indal
    0.90
    ping
    0.89
    hee
    0.89
    Activations Density 0.022%

    No Known Activations