© 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. 7-RES-JB
    11. 21731
    Prev
    Next
    INDEX
    Explanations

    groups of people or professions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.75
    atever
    -0.63
    ield
    -0.60
    forward
    -0.60
    forestation
    -0.59
     Forward
    -0.59
    BALL
    -0.57
    Specific
    -0.57
    ļéĨĴ
    -0.57
     Last
    -0.56
    POSITIVE LOGITS
    folk
    1.16
     themselves
    1.06
    ']
    0.96
    '
    0.95
     involved
    0.88
    hest
    0.84
    layer
    0.83
    iest
    0.82
     composing
    0.79
    hip
    0.77
    Activations Density 0.306%

    No Known Activations