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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22746
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions directed towards objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of lifting, breaking, or moving objects

    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
    interstitial
    -0.64
     DEFENSE
    -0.61
     Annotations
    -0.59
     divergence
    -0.58
     Defendants
    -0.57
     tert
    -0.56
     Featured
    -0.56
     Occupations
    -0.55
     departures
    -0.55
     backdrop
    -0.54
    POSITIVE LOGITS
     cheaply
    0.88
    handedly
    0.87
     nicely
    0.86
     yourself
    0.85
     somew
    0.84
     roy
    0.81
     herself
    0.78
     yourselves
    0.78
     gently
    0.77
     properly
    0.77
    Activations Density 0.148%

    No Known Activations