© 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. 11-RES-JB
    11. 22574
    Prev
    Next
    INDEX
    Explanations

    names of researchers and scientists

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of researchers and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricane
    -0.76
     mileage
    -0.75
     living
    -0.72
     prime
    -0.71
     continual
    -0.71
     Teddy
    -0.71
     totality
    -0.70
     creatively
    -0.70
     billboards
    -0.70
     successive
    -0.69
    POSITIVE LOGITS
    inav
    1.32
    essler
    1.31
    ohl
    1.27
    ijn
    1.26
    itsch
    1.25
    ijk
    1.22
    abet
    1.21
    atz
    1.21
    ör
    1.20
    idth
    1.20
    Activations Density 0.163%

    No Known Activations