© 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 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. 2-RES-JB
    11. 15843
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "The Walking Dead"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "walking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    si
    -0.79
    cms
    -0.78
    nery
    -0.78
    yon
    -0.77
    pps
    -0.75
    xy
    -0.74
    nings
    -0.71
    aments
    -0.71
    ifi
    -0.70
    tml
    -0.69
    POSITIVE LOGITS
     exha
    0.91
    redients
    0.80
     behavi
    0.78
     suspic
    0.74
    GGGGGGGG
    0.74
     conduc
    0.73
     rats
    0.73
     ability
    0.69
     alcoholic
    0.69
     conflic
    0.68
    Activations Density 0.145%

    No Known Activations