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. 0-RES-JB
    6. 11052
    Prev
    Next
    INDEX
    Explanations

    words related to locks and lockouts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions or blockades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comed
    -0.71
    chio
    -0.70
     Palin
    -0.66
     plotting
    -0.65
     Fried
    -0.64
     Beir
    -0.63
     Romantic
    -0.63
    Winged
    -0.63
    plot
    -0.63
     von
    -0.62
    POSITIVE LOGITS
     locks
    2.59
     lockout
    2.19
    locks
    1.84
     squat
    1.70
     lockdown
    1.69
     barric
    1.57
     locking
    1.53
     lock
    1.31
     squats
    1.28
    locking
    1.23
    Activations Density 0.030%

    No Known Activations