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. 14701
    Prev
    Next
    INDEX
    Explanations

    instances of the word "North Carolina."

    oai_token-act-pair · gpt-3.5-turbo

    instances and mentions of "North Carolina."

    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
    lords
    -0.80
    Lens
    -0.79
    bats
    -0.78
    alty
    -0.77
    shake
    -0.76
    matically
    -0.76
    uably
    -0.76
    sch
    -0.73
    sett
    -0.73
    gerald
    -0.71
    POSITIVE LOGITS
     Hurricanes
    0.95
     State
    0.90
    olina
    0.90
    urses
    0.90
     Carolina
    0.89
     Courage
    0.89
     Herrera
    0.83
    sylvania
    0.81
     Edison
    0.81
    ļéĨĴ
    0.80
    Activations Density 0.014%

    No Known Activations