Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24267
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts related to copying, pasting, and other functions

    oai_token-act-pair · gpt-3.5-turbo

    keyboard shortcuts and command-related phrases

    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
    cdn
    -0.76
     Dion
    -0.75
     creditor
    -0.71
    BuyableInstoreAndOnline
    -0.69
     virginity
    -0.67
     biod
    -0.66
     Ukrain
    -0.65
     debts
    -0.64
     Flor
    -0.63
    amation
    -0.62
    POSITIVE LOGITS
     Ctrl
    1.47
     CTRL
    1.43
    Ctrl
    1.35
     Shift
    1.33
    ctrl
    1.32
    Shift
    1.31
    trl
    1.21
     mouse
    1.19
    Cmd
    1.17
    Alt
    1.17
    Activations Density 0.118%

    No Known Activations