© 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. 3-RES-JB
    11. 6277
    Prev
    Next
    INDEX
    Explanations

    the name "Mick" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.87
    FUL
    -0.76
    Interstitial
    -0.75
    flies
    -0.72
    raints
    -0.70
    DragonMagazine
    -0.68
    perse
    -0.68
    BIP
    -0.66
    doors
    -0.65
    enture
    -0.64
    POSITIVE LOGITS
     Mick
    1.04
    igans
    0.89
    eter
    0.86
    athon
    0.84
    aroo
    0.84
    iewicz
    0.84
    erson
    0.83
     Foley
    0.83
    angelo
    0.82
    ulas
    0.81
    Activations Density 0.003%

    No Known Activations