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

    Neuronpedia

    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. 1-RES-JB
    11. 22781
    Prev
    Next
    INDEX
    Explanations

    timestamps of sports programs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports networks and broadcasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opol
    -0.81
    atron
    -0.79
    obic
    -0.75
    rail
    -0.74
    agen
    -0.74
    roman
    -0.72
    aga
    -0.71
    cht
    -0.70
    ahn
    -0.70
    ag
    -0.70
    POSITIVE LOGITS
    BOOK
    1.39
    DOWN
    1.34
    HEAD
    1.33
     FANTASY
    1.33
    BACK
    1.30
    STER
    1.28
     FORM
    1.28
    LY
    1.27
    NAME
    1.27
    ERAL
    1.25
    Activations Density 0.098%

    No Known Activations