© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18610
    Prev
    Next
    INDEX
    Explanations

    adjectives relating to intensity or extreme situations

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe negative or complex situations

    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
    ORED
    -0.79
    udder
    -0.77
    registered
    -0.76
    hots
    -0.73
    also
    -0.73
     Lastly
    -0.73
    FIR
    -0.71
    oaded
    -0.71
     [|
    -0.71
    each
    -0.70
    POSITIVE LOGITS
     nature
    1.55
    ness
    1.47
     workings
    1.26
     ramifications
    1.25
     implications
    1.23
     effects
    1.19
     complexities
    1.17
     realities
    1.12
     consequences
    1.12
     confines
    1.11
    Activations Density 0.313%

    No Known Activations