© 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. 7-RES-JB
    11. 23853
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific sports team or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amen
    -0.73
    tones
    -0.69
    unci
    -0.67
     panels
    -0.67
    geries
    -0.64
    activ
    -0.63
     Pew
    -0.62
    cens
    -0.61
     Panc
    -0.61
    Posts
    -0.60
    POSITIVE LOGITS
    're
    1.14
    've
    1.12
     scrimmage
    1.03
    'll
    0.99
    ldon
    0.81
     owe
    0.80
     fielded
    0.78
     lineback
    0.77
     preseason
    0.77
     scored
    0.75
    Activations Density 0.164%

    No Known Activations