© 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. 0-RES-JB
    11. 2015
    Prev
    Next
    INDEX
    Explanations

    references to werewolves

    oai_token-act-pair · gpt-3.5-turbo

    references to wolves and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ident
    -0.75
     Bris
    -0.72
     eq
    -0.67
     iod
    -0.65
     suscept
    -0.65
     mant
    -0.64
     dehyd
    -0.63
     contrad
    -0.62
     ensu
    -0.62
     compuls
    -0.61
    POSITIVE LOGITS
    wolf
    2.93
    edia
    2.22
    wolves
    2.07
    kick
    1.53
    actic
    1.44
    kus
    1.31
     Mellon
    1.24
    thought
    1.11
    weights
    1.09
     Turing
    1.07
    Activations Density 0.037%

    No Known Activations