© 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. 22126
    Prev
    Next
    INDEX
    Explanations

    phrases related to layers or hidden aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to something situated below or hidden beneath the surface

    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
    eln
    -0.82
    ordan
    -0.81
    yah
    -0.73
    iji
    -0.71
    atic
    -0.71
    zai
    -0.71
    za
    -0.70
    itar
    -0.68
    ³³³³³³³³³³³³³³³³
    -0.67
     Glob
    -0.66
    POSITIVE LOGITS
    neath
    1.04
    eatures
    0.98
    ĸļ
    0.89
     layers
    0.89
    pins
    0.85
    sea
    0.81
     beneath
    0.79
    ĨĴ
    0.79
     lip
    0.78
    İĭ
    0.77
    Activations Density 0.019%

    No Known Activations