© 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. 11-RES-JB
    11. 24095
    Prev
    Next
    INDEX
    Explanations

    verbs related to various abilities or skills

    oai_token-act-pair · gpt-3.5-turbo

    references to ability and effectiveness in performing tasks or duties

    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
    lehem
    -0.77
    tops
    -0.77
    soDeliveryDate
    -0.73
    warming
    -0.71
    cloth
    -0.70
    bats
    -0.69
     Loren
    -0.67
    listed
    -0.66
    LESS
    -0.65
    lights
    -0.65
    POSITIVE LOGITS
     innovate
    1.44
     navigate
    1.34
     withstand
    1.33
     respond
    1.30
     cope
    1.27
     mobilize
    1.25
     communicate
    1.25
     execute
    1.25
     engage
    1.22
     detect
    1.20
    Activations Density 0.201%

    No Known Activations