© 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. 8-RES-JB
    11. 22266
    Prev
    Next
    INDEX
    Explanations

    words related to sports positions, such as "starting guard" or "starting forward"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "starting" in relation to jobs or positions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -1.01
    ingly
    -0.89
    idon
    -0.88
    ably
    -0.86
    bey
    -0.84
    ertodd
    -0.81
    nery
    -0.81
    hooting
    -0.80
    metic
    -0.80
    greg
    -0.78
    POSITIVE LOGITS
     pitcher
    1.01
     lineup
    0.95
     XI
    0.92
     pitching
    0.86
     pitchers
    0.86
     goaltender
    0.85
     goalie
    0.82
     position
    0.80
     point
    0.79
     quarterback
    0.79
    Activations Density 0.034%

    No Known Activations