© 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. 4-RES-JB
    11. 9282
    Prev
    Next
    INDEX
    Explanations

    words related to the basketball position of "point guard."

    oai_token-act-pair · gpt-3.5-turbo

    instances of "guard" related to basketball positions

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

    No Comments

    Negative Logits
     annexed
    -0.63
     scaven
    -0.62
     occupant
    -0.62
     disclosure
    -0.61
    ibal
    -0.61
    ombat
    -0.60
    edition
    -0.58
     lenders
    -0.57
    sth
    -0.57
    emon
    -0.57
    POSITIVE LOGITS
    iola
    0.80
    adin
    0.76
    anova
    0.75
     =================
    0.70
    ery
    0.70
    ocally
    0.69
    ettes
    0.69
     Jerome
    0.68
    tackle
    0.67
    lake
    0.65
    Activations Density 0.014%

    No Known Activations