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. 0-RES-JB
    6. 7256
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Tennessee"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tenn" and its variations, likely referencing the state of Tennessee

    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
    angler
    -0.91
     Chile
    -0.80
     Bundle
    -0.78
     Bears
    -0.78
    Dutch
    -0.76
    Scot
    -0.71
    ball
    -0.71
     Tracker
    -0.70
     Floyd
    -0.70
    cius
    -0.68
    POSITIVE LOGITS
     Sana
    2.66
     Haj
    1.87
    adiq
    1.51
     Kens
    1.50
     Tenn
    1.37
     Sakuya
    1.23
     Enix
    1.22
     Jinn
    1.20
     Shinji
    1.17
     Aman
    1.17
    Activations Density 0.079%

    No Known Activations