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

    Neuronpedia

    Jacobian LensNEW
    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. 17666
    Prev
    Next
    INDEX
    Explanations

    quantitative information related to numerical values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "number" followed by numerical values

    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
    merce
    -0.71
    robe
    -0.68
    Materials
    -0.67
     Passage
    -0.65
     Despair
    -0.65
    INTON
    -0.64
    imar
    -0.62
     Conditions
    -0.61
     paradise
    -0.60
    _-
    -0.59
    POSITIVE LOGITS
     numbers
    0.85
    number
    0.85
     number
    0.80
    NUM
    0.79
    enance
    0.77
    naires
    0.76
    plate
    0.76
    plates
    0.74
     Numbers
    0.71
    metry
    0.71
    Activations Density 0.039%

    No Known Activations