© 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. 11-RES-JB
    11. 20973
    Prev
    Next
    INDEX
    Explanations

    information related to accidents or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and conditions affecting groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gran
    -0.74
    sweet
    -0.73
    isite
    -0.70
    ĸļ
    -0.67
    hig
    -0.67
    ascus
    -0.66
    Sweet
    -0.66
    grade
    -0.64
     Unleashed
    -0.64
    ãĤ´ãĥ³
    -0.64
    POSITIVE LOGITS
     people
    2.05
    people
    1.89
     persons
    1.80
    People
    1.76
     People
    1.66
     person
    1.60
     individuals
    1.55
     PEOPLE
    1.53
     folks
    1.48
     Persons
    1.39
    Activations Density 0.302%

    No Known Activations