© 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
    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. 22581
    Prev
    Next
    INDEX
    Explanations

    words related to the title "citizen" or military rank "lieutenant"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to notable individuals or entities

    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
    Ļ½
    -0.84
    colour
    -0.80
     Essence
    -0.72
     colour
    -0.70
     Celt
    -0.66
     coloured
    -0.66
    Ħ¢
    -0.66
     Inquiry
    -0.66
     lad
    -0.66
     RFC
    -0.65
    POSITIVE LOGITS
    itar
    3.17
    arro
    2.28
    arre
    1.64
    okin
    1.29
    inelli
    1.24
    urai
    1.20
    itars
    1.15
    istar
    1.10
    stead
    1.08
    arette
    1.03
    Activations Density 0.037%

    No Known Activations