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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16176
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone finishing a task or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to players coming off the field or bench in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MX
    -0.72
     Omn
    -0.65
     magnets
    -0.64
     liter
    -0.63
     ECO
    -0.62
    anners
    -0.62
    zanne
    -0.61
    ãĥį
    -0.60
    Export
    -0.60
    ISM
    -0.60
    POSITIVE LOGITS
    ansas
    0.80
    ibaba
    0.73
     waivers
    0.72
    season
    0.68
     reliever
    0.67
     Jag
    0.67
    nar
    0.67
    screen
    0.67
     hitters
    0.66
    loading
    0.66
    Activations Density 0.044%

    No Known Activations