Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24431
    Prev
    Next
    INDEX
    Explanations

    terms related to stealing or looting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theft and looting

    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
     pairing
    -0.72
     Evan
    -0.69
    sen
    -0.68
    cond
    -0.66
     Adelaide
    -0.66
    uter
    -0.65
     Dennis
    -0.65
     Connie
    -0.65
     Intermediate
    -0.65
     Standards
    -0.63
    POSITIVE LOGITS
     loot
    3.78
     looting
    3.15
     looted
    2.69
     Loot
    2.47
     plunder
    2.34
     hoard
    1.53
     raiding
    1.38
     spo
    1.34
     thieves
    1.28
     scaven
    1.27
    Activations Density 0.013%

    No Known Activations