© 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. 21869
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing work or projects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "working."

    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
    cffff
    -0.71
    é¾įå
    -0.64
    efe
    -0.63
    idences
    -0.62
    ython
    -0.61
    Failure
    -0.60
    mosp
    -0.60
    ritical
    -0.60
    ailability
    -0.59
    apego
    -0.57
    POSITIVE LOGITS
     diligently
    1.18
     furiously
    1.18
     fever
    1.08
     tirelessly
    1.08
     towards
    1.04
     toward
    1.03
     frantically
    1.02
     overtime
    0.96
     closely
    0.95
     on
    0.91
    Activations Density 0.069%

    No Known Activations