© 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 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. 10-RES-JB
    11. 4628
    Prev
    Next
    INDEX
    Explanations

    words related to time efficiency and cost effectiveness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to efficiency and the impact of various factors on life and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waivers
    -0.67
    ibraries
    -0.66
     Bans
    -0.63
     Contracts
    -0.63
     NCT
    -0.62
     designation
    -0.61
    clerosis
    -0.61
     Streets
    -0.61
    uctions
    -0.61
     Medline
    -0.60
    POSITIVE LOGITS
    ful
    1.40
    less
    1.35
    worthy
    1.24
    ious
    1.21
    friendly
    1.19
    able
    1.19
    icky
    1.15
    full
    1.15
    oriented
    1.11
    acious
    1.10
    Activations Density 0.313%

    No Known Activations