© 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. 4-RES-JB
    11. 6410
    Prev
    Next
    INDEX
    Explanations

    large numerical values without specific context

    oai_token-act-pair · gpt-3.5-turbo

    numerical data indicating statistics or financial figures

    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
    Crime
    -0.76
    ²¾
    -0.75
     corrid
    -0.70
    ulet
    -0.68
    sole
    -0.68
    inav
    -0.66
    pty
    -0.62
     citiz
    -0.60
     Pict
    -0.60
     encount
    -0.59
    POSITIVE LOGITS
    ths
    0.92
     lbs
    0.88
     ±
    0.83
    IU
    0.78
     pounds
    0.78
    mx
    0.73
     miles
    0.71
     gallons
    0.71
     tonnes
    0.71
    /-
    0.70
    Activations Density 0.079%

    No Known Activations