© 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. 2-RES-JB
    11. 16035
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Daytona"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, particularly "Dayton" and "Akron."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.84
    encer
    -0.80
    encers
    -0.77
    ystem
    -0.74
    ulative
    -0.72
    ATHER
    -0.70
    Correction
    -0.67
    ences
    -0.67
    bery
    -0.66
    ionage
    -0.66
    POSITIVE LOGITS
     Sparkle
    0.81
     Dayton
    0.80
    £ı
    0.79
     Township
    0.74
    ©¶æ¥µ
    0.71
    hyde
    0.69
    mouth
    0.67
    oked
    0.67
    anus
    0.66
    mega
    0.66
    Activations Density 0.007%

    No Known Activations