© 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. 6-RES-JB
    11. 2975
    Prev
    Next
    INDEX
    Explanations

    terms related to financial concepts like "offset" or "budget cuts"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to offsets in various contexts, including financial and scientific

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRIP
    -0.73
    Export
    -0.71
    NetMessage
    -0.66
    Interstitial
    -0.64
    ostic
    -0.64
    trl
    -0.64
    ovych
    -0.64
    anyon
    -0.64
    json
    -0.62
    wordpress
    -0.62
    POSITIVE LOGITS
    ting
    1.39
    mented
    1.01
    ted
    0.97
    ments
    0.90
    aneous
    0.84
    ment
    0.83
    aria
    0.74
    balanced
    0.70
    ania
    0.69
    balance
    0.69
    Activations Density 0.027%

    No Known Activations