© 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. 6952
    Prev
    Next
    INDEX
    Explanations

    mentions of positions on a sports team, particularly focusing on midfield players

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the positions and roles of players in sports, particularly focusing on midfield positions

    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
    displayText
    -0.85
    Downloadha
    -0.83
    igslist
    -0.78
    abul
    -0.77
    imaru
    -0.76
    mingham
    -0.75
    sbm
    -0.73
     Canaver
    -0.73
    cale
    -0.72
     Norton
    -0.72
    POSITIVE LOGITS
    ers
    1.01
     positions
    0.91
     position
    0.85
     slot
    0.83
     duo
    0.82
     slots
    0.80
    ership
    0.77
     lan
    0.77
     trio
    0.76
     talent
    0.76
    Activations Density 0.031%

    No Known Activations