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. 6-RES-JB
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    people holding or clutching objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "holding."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esters
    -0.81
    Month
    -0.76
    itters
    -0.74
    hemer
    -0.73
    ixels
    -0.71
    isan
    -0.70
    ode
    -0.70
    MQ
    -0.70
    undown
    -0.70
    ema
    -0.70
    POSITIVE LOGITS
     luggage
    0.87
     loads
    0.78
    handle
    0.76
    tons
    0.76
    holding
    0.74
     bags
    0.74
     scissors
    0.73
     shoulder
    0.72
     knives
    0.71
     trophies
    0.70
    Activations Density 0.079%

    No Known Activations