© 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. 17265
    Prev
    Next
    INDEX
    Explanations

    phrases indicating choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" used in various contexts

    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
    ernels
    -0.95
    lees
    -0.91
    flows
    -0.81
    doms
    -0.80
     Attacks
    -0.78
     Accounts
    -0.77
    kins
    -0.76
    ouses
    -0.76
    Rs
    -0.76
    akes
    -0.75
    POSITIVE LOGITS
     bracelet
    0.94
     charger
    0.91
     pamphlet
    0.88
     a
    0.86
    chard
    0.85
     two
    0.84
     necklace
    0.84
     thinker
    0.84
     proposition
    0.84
     piece
    0.84
    Activations Density 0.185%

    No Known Activations