© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 16920
    Prev
    Next
    INDEX
    Explanations

    names or combinations of letters with the pattern "letter<tab>8"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Induction Feature
    its an induction feature

    No Comments

    Negative Logits
    è»
    -0.85
     Gaw
    -0.76
     Mount
    -0.72
    Gra
    -0.71
     PACK
    -0.70
     caval
    -0.69
     gra
    -0.68
    ::::::::
    -0.68
     polic
    -0.68
     Warfare
    -0.67
    POSITIVE LOGITS
    ins
    1.54
    in
    1.44
    IN
    1.35
    inian
    1.35
    inis
    1.34
    iner
    1.28
    ino
    1.28
    ini
    1.23
    inse
    1.21
    inia
    1.20
    Activations Density 0.139%

    No Known Activations