© 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. 8-RES-JB
    11. 12241
    Prev
    Next
    INDEX
    Explanations

    text related to people's names ending with 'od' and 'odie'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "od."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leone
    -0.71
     Ago
    -0.66
    UGE
    -0.64
    terday
    -0.60
     Faul
    -0.60
    ORTS
    -0.59
     Lafayette
    -0.57
     Canter
    -0.56
     Irma
    -0.56
     Goat
    -0.55
    POSITIVE LOGITS
    yssey
    1.45
    ragon
    1.07
    sworth
    1.07
    iox
    1.06
    iamond
    1.04
    iversity
    1.02
    rome
    1.01
    rama
    0.97
    ynamic
    0.96
    amn
    0.96
    Activations Density 0.036%

    No Known Activations