© 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. 12394
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Grady" with varying levels of activation strength

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the suffix 'ady'

    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
    falls
    -0.74
    uring
    -0.72
    UME
    -0.69
    IBLE
    -0.67
    oppy
    -0.67
    ayers
    -0.67
    uckland
    -0.66
    olated
    -0.65
     drilled
    -0.65
    bows
    -0.64
    POSITIVE LOGITS
    rov
    0.92
    ILY
    0.77
    jet
    0.77
    illac
    0.76
     Creatures
    0.75
    ady
    0.74
    mbol
    0.74
    arov
    0.73
    cade
    0.71
    ptoms
    0.70
    Activations Density 0.014%

    No Known Activations