© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15453
    Prev
    Next
    INDEX
    Explanations

    measurements, specifically related to length or size

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements and terms related to physical sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feral
    -0.71
     punct
    -0.69
     liv
    -0.68
     wi
    -0.68
     artic
    -0.67
     rupture
    -0.66
     lett
    -0.66
     shr
    -0.66
     flex
    -0.65
     Cruel
    -0.64
    POSITIVE LOGITS
    meter
    3.97
    azar
    1.04
    male
    1.01
    met
    0.99
    metry
    0.96
    docker
    0.95
    hare
    0.95
    MET
    0.95
     Meter
    0.93
    asar
    0.92
    Activations Density 0.031%

    No Known Activations