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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6806
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or places, particularly "across the country"

    oai_token-act-pair · gpt-3.5-turbo

    references to "country" and "nation" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    char
    -0.74
    imon
    -0.68
     RIS
    -0.65
    changes
    -0.64
     Prelude
    -0.63
     Gaw
    -0.63
     MG
    -0.63
    enhagen
    -0.62
     Cly
    -0.61
    Lua
    -0.61
    POSITIVE LOGITS
    wide
    1.01
     illegally
    0.76
    ADA
    0.75
    isphere
    0.75
     converge
    0.73
    men
    0.70
    hurst
    0.70
     conver
    0.69
    idas
    0.69
     skyline
    0.67
    Activations Density 0.064%

    No Known Activations