© 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. 10663
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "DO" combined with a single-digit numerical value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "DO" related to different contexts

    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
    ulates
    -0.78
    Reviewer
    -0.75
    ulating
    -0.74
    ulated
    -0.74
    ulations
    -0.74
    laus
    -0.67
     Handling
    -0.66
    Gaza
    -0.66
    ulative
    -0.64
    ulatory
    -0.64
    POSITIVE LOGITS
    herty
    1.23
    ppel
    1.11
    omsday
    1.05
    ctr
    0.99
    oms
    0.98
    zens
    0.94
    jo
    0.88
    omed
    0.87
    lez
    0.87
    lyak
    0.85
    Activations Density 0.030%

    No Known Activations