© 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. 7-RES-JB
    11. 12412
    Prev
    Next
    INDEX
    Explanations

    numerical quantities related to quantities of people or objects

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estine
    -0.89
    estate
    -0.73
    nam
    -0.70
    abol
    -0.68
    alyses
    -0.66
     symmetry
    -0.65
    warts
    -0.64
    money
    -0.64
    aker
    -0.64
    hran
    -0.64
    POSITIVE LOGITS
    px
    1.04
    lbs
    1.03
     lbs
    0.99
     pounds
    0.98
     miles
    0.96
    lb
    0.94
     MHz
    0.93
     metres
    0.93
     kilometers
    0.93
    +
    0.91
    Activations Density 0.086%

    No Known Activations