© 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. 12913
    Prev
    Next
    INDEX
    Explanations

    common phrases or concepts modified by the word "many."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of abundance or variety

    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
    ENCE
    -0.84
    anism
    -0.81
    slaught
    -0.81
    arenthood
    -0.76
    inth
    -0.75
    athon
    -0.74
    assisted
    -0.73
    ãĥ¼ãĥ«
    -0.73
    Mob
    -0.73
    obook
    -0.73
    POSITIVE LOGITS
     reasons
    1.52
     ways
    1.52
     exceptions
    1.27
     occasions
    1.26
     similarities
    1.21
     caveats
    1.20
     unanswered
    1.19
     possibilities
    1.18
     examples
    1.17
     instances
    1.17
    Activations Density 0.180%

    No Known Activations