© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "DO" with a numeric value indicating relevance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "DO" in various contexts, especially related to organizational references

    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
    Gaza
    -0.72
    ipel
    -0.71
    deck
    -0.70
    mere
    -0.67
     Austral
    -0.66
    Reviewer
    -0.66
     totality
    -0.65
    mble
    -0.65
    pter
    -0.65
    itatively
    -0.64
    POSITIVE LOGITS
    CT
    0.95
    FILE
    0.86
    OME
    0.85
     NOT
    0.84
    omsday
    0.82
    OR
    0.80
    ORS
    0.80
    OM
    0.80
    omed
    0.80
    女
    0.79
    Activations Density 0.005%

    No Known Activations