© 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. 2-RES-JB
    11. 17454
    Prev
    Next
    INDEX
    Explanations

    names of individual people

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific individuals and legal terminology

    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
     Galile
    -0.81
     harvest
    -0.77
    iour
    -0.76
     crop
    -0.73
     Gerr
    -0.72
     Asc
    -0.65
     Gujar
    -0.64
    ophe
    -0.64
    arro
    -0.64
    iewicz
    -0.63
    POSITIVE LOGITS
    abled
    1.01
    ldom
    0.99
    rine
    0.87
    borg
    0.85
    OTUS
    0.82
    verend
    0.79
    adium
    0.77
    kamp
    0.76
    vironment
    0.75
    mberg
    0.75
    Activations Density 0.020%

    No Known Activations