© 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. 3-RES-JB
    11. 23348
    Prev
    Next
    INDEX
    Explanations

    numerical values and years within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific numerical values

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ique
    -0.81
    ivity
    -0.79
    ional
    -0.78
    cil
    -0.76
    rophe
    -0.74
    shire
    -0.74
    ezvous
    -0.73
    icularly
    -0.71
    mire
    -0.71
    cies
    -0.70
    POSITIVE LOGITS
     externalToEVAOnly
    1.02
    mph
    0.91
    989
    0.90
    98
    0.88
    794
    0.88
    987
    0.85
    765
    0.85
    58
    0.81
    80
    0.81
    68
    0.80
    Activations Density 0.053%

    No Known Activations