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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4595
    Prev
    Next
    INDEX
    Explanations

    references to bidding or competition in business or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to bidding and associated entities or characteristics

    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
     Allies
    -0.72
    Ĥİ
    -0.69
     Pants
    -0.68
     tanks
    -0.68
     strut
    -0.66
     Nazis
    -0.65
     Painter
    -0.64
     parach
    -0.64
     hooks
    -0.64
    ))))
    -0.62
    POSITIVE LOGITS
    bid
    3.11
    idian
    1.47
    tom
    1.29
    Tom
    1.24
    Digital
    1.19
    chid
    1.08
    requ
    1.04
    avid
    1.00
     Eb
    0.94
     Townsend
    0.92
    Activations Density 0.058%

    No Known Activations