© 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. 10-RES-JB
    11. 14094
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    geographic or organizational names and terms

    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
     similar
    -0.71
     warranty
    -0.68
     alt
    -0.64
     overw
    -0.64
     visible
    -0.62
     routine
    -0.62
     concealed
    -0.62
     masked
    -0.62
     prior
    -0.62
     worthwhile
    -0.61
    POSITIVE LOGITS
    assian
    1.13
    elia
    1.08
    leton
    1.08
    ley
    1.00
    ena
    1.00
    hani
    1.00
    ham
    0.98
    hart
    0.97
    ayne
    0.96
    ford
    0.96
    Activations Density 0.187%

    No Known Activations