© 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. 0-RES-JB
    11. 2188
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a particular individual

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or references to a specific name or term

    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
     stream
    -0.71
     remote
    -0.70
     FIRE
    -0.69
     streams
    -0.68
     shout
    -0.65
     things
    -0.62
     shining
    -0.62
     ceilings
    -0.60
     fixed
    -0.60
     flip
    -0.59
    POSITIVE LOGITS
    agen
    4.77
    ogen
    1.37
    ager
    1.35
    agon
    1.32
    agan
    1.24
    ogene
    1.23
    aging
    1.21
    agin
    1.17
    ogens
    1.13
    ag
    1.07
    Activations Density 0.009%

    No Known Activations