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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10274
    Prev
    Next
    INDEX
    Explanations

    numeric digits

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values, specifically digits and terms associated with them

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

    No Comments

    Negative Logits
    hire
    -0.94
    lain
    -0.82
    ouf
    -0.77
     Shield
    -0.73
    Study
    -0.72
    heres
    -0.70
    nd
    -0.68
    dep
    -0.67
    side
    -0.66
    lace
    -0.65
    POSITIVE LOGITS
     digit
    0.93
    itial
    0.90
    osaurs
    0.90
    ized
    0.89
     digits
    0.89
    igr
    0.87
     ILCS
    0.86
    oded
    0.85
    digit
    0.85
    itized
    0.84
    Activations Density 0.014%

    No Known Activations