© 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. 2-RES-JB
    11. 4088
    Prev
    Next
    INDEX
    Explanations

    words related to skills and attributes in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    nouns and phrases related to sports and player performance

    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
     Surve
    -0.72
     Tablet
    -0.71
     PBS
    -0.70
     Parties
    -0.67
     ®
    -0.67
     Access
    -0.66
    ya
    -0.65
     Feminist
    -0.64
    tein
    -0.64
    POL
    -0.63
    POSITIVE LOGITS
     offensively
    0.99
     positional
    0.98
     teammates
    0.97
     rookies
    0.97
     inexper
    0.96
     rookie
    0.96
     talent
    0.93
     teammate
    0.92
     hitters
    0.92
     linem
    0.92
    Activations Density 0.495%

    No Known Activations