© 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 EvalsExportsinterp-engineNEWAPI 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. 4199
    Prev
    Next
    INDEX
    Explanations

    big numbers related to human activities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantities and large numbers related to populations or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ivist
    -0.72
    itiz
    -0.71
    vil
    -0.67
     suprem
    -0.66
    Cru
    -0.64
    sole
    -0.61
    fun
    -0.61
    along
    -0.60
    aul
    -0.60
    querque
    -0.58
    POSITIVE LOGITS
     pounds
    0.99
    gp
    0.93
     hectares
    0.92
     dollars
    0.91
    +)
    0.85
     tonnes
    0.84
     lbs
    0.84
     acres
    0.80
    bps
    0.78
     euros
    0.77
    Activations Density 0.076%

    No Known Activations