© 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. 10-RES-JB
    11. 2258
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the direction or trend of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating directionality or trends related to progress or decline

    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
    yrs
    -0.60
    ère
    -0.58
     perched
    -0.58
    ulner
    -0.57
     ingested
    -0.57
    mere
    -0.56
     reprinted
    -0.55
    icity
    -0.55
     CLA
    -0.55
    Availability
    -0.54
    POSITIVE LOGITS
     direction
    1.89
     directions
    1.73
     opposite
    1.21
    direction
    1.13
     Direction
    1.13
     footsteps
    1.11
     circles
    1.06
    wards
    1.05
    eways
    0.95
    oward
    0.95
    Activations Density 0.127%

    No Known Activations