© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    terms related to boys or male individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boys" and related variations indicating a group of male children or adolescents

    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
    kson
    -0.73
    olson
    -0.69
    atively
    -0.67
    uits
    -0.65
     palms
    -0.64
     Fallon
    -0.61
     canopy
    -0.60
     trial
    -0.60
    ukemia
    -0.59
    urses
    -0.59
    POSITIVE LOGITS
    awei
    0.90
    rahim
    0.87
    inary
    0.82
    Bey
    0.81
    dinand
    0.78
    Wan
    0.77
    boy
    0.71
    Mag
    0.70
    doms
    0.70
    rieved
    0.69
    Activations Density 0.027%

    No Known Activations