© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 1855
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially mentioning "Dayton" and "Daytona."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the locations "Dayton" and "Akron."

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

    No Comments

    Negative Logits
    ystem
    -0.84
    encer
    -0.76
    ahime
    -0.74
    ariat
    -0.72
    berman
    -0.70
    atorial
    -0.69
    ATHER
    -0.68
    ulative
    -0.68
    encers
    -0.67
    ¯¯¯¯
    -0.67
    POSITIVE LOGITS
     Township
    0.76
     Dillon
    0.71
     Dayton
    0.71
     Sparkle
    0.70
    hof
    0.67
    hurst
    0.67
     Rat
    0.67
    oked
    0.65
     Hendricks
    0.65
     Congo
    0.64
    Activations Density 0.015%

    No Known Activations