© 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. 24567
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms, potentially related to a particular entity or individual named "Caballero"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    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
    achev
    -0.80
     tremend
    -0.76
    manship
    -0.69
    ovych
    -0.67
     metab
    -0.65
     encode
    -0.65
    uthor
    -0.64
    hoff
    -0.62
    oppable
    -0.62
    tein
    -0.61
    POSITIVE LOGITS
    igham
    0.82
    xus
    0.80
    estial
    0.77
    ornia
    0.74
    ulhu
    0.73
    uve
    0.72
     Blanc
    0.72
    ulas
    0.71
    owder
    0.69
    opolis
    0.69
    Activations Density 0.503%

    No Known Activations