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. 3-RES-JB
    6. 19399
    Prev
    Next
    INDEX
    Explanations

    semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dates in the format of days, months, and years

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spons
    -0.97
    ħĭ
    -0.87
     tremend
    -0.83
     destro
    -0.81
     attacker
    -0.79
     unnecess
    -0.78
    bledon
    -0.76
     millenn
    -0.76
    icter
    -0.76
     unbeat
    -0.75
    POSITIVE LOGITS
    -)
    1.00
    ;;;;;;;;;;;;
    0.83
    alias
    0.79
    +)
    0.76
    }"
    0.75
     };
    0.73
     Ranch
    0.71
     Spread
    0.70
    fa
    0.68
     ;;
    0.68
    Activations Density 0.044%

    No Known Activations