© 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 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. 2-RES-JB
    11. 459
    Prev
    Next
    INDEX
    Explanations

    the word "school"

    oai_token-act-pair · gpt-4-turbo

    references to educational institutions, specifically the word "school."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "school."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tame
    -0.75
     Bundy
    -0.66
    vernment
    -0.66
     dormant
    -0.65
    OPLE
    -0.65
     live
    -0.62
     genus
    -0.61
    \\\\
    -0.61
     recoil
    -0.61
     LIVE
    -0.58
    POSITIVE LOGITS
    kids
    1.17
    girls
    1.12
    children
    1.11
    masters
    1.09
    boy
    1.02
    boys
    1.01
    master
    0.93
    neys
    0.91
    girl
    0.91
    essor
    0.86
    Activations Density 0.038%

    No Known Activations