© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12505
    Prev
    Next
    INDEX
    Explanations

    mentions of computer chips

    oai_token-act-pair · gpt-3.5-turbo

    references to chips, particularly in a technological context

    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
    ctic
    -0.70
     Nordic
    -0.68
     Scandinavian
    -0.68
    lihood
    -0.66
     gearing
    -0.65
     Camden
    -0.64
    Operation
    -0.63
     Scandinav
    -0.63
     Belarus
    -0.62
    ROR
    -0.62
    POSITIVE LOGITS
    otle
    1.33
     chips
    1.23
     Chips
    1.12
    ets
    1.07
    pots
    1.03
     flakes
    0.93
     chip
    0.93
     implanted
    0.91
    arettes
    0.90
    chip
    0.90
    Activations Density 0.008%

    No Known Activations