© 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. 6-RES-JB
    6. 13702
    Prev
    Next
    INDEX
    Explanations

    URLs and website links

    oai_token-act-pair · gpt-3.5-turbo

    URLs and file paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angry
    -0.72
     hugged
    -0.70
     apologised
    -0.69
     Ammo
    -0.69
     creep
    -0.69
     creeping
    -0.68
     Romo
    -0.66
     hugging
    -0.65
     wards
    -0.64
     enraged
    -0.64
    POSITIVE LOGITS
    index
    1.24
    comments
    1.11
    etc
    1.09
    sites
    1.07
    photos
    1.04
    products
    1.04
    dq
    1.03
    detail
    1.03
    archives
    1.01
    Pages
    1.01
    Activations Density 0.036%

    No Known Activations