© 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. 6-RES-JB
    11. 11748
    Prev
    Next
    INDEX
    Explanations

    references to unlimited plans or services

    oai_token-act-pair · gpt-3.5-turbo

    references to unlimited services, particularly in relation to data plans

    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
    iquette
    -0.84
    geist
    -0.77
    acle
    -0.76
    bourg
    -0.72
    olith
    -0.69
    ochemical
    -0.69
    icho
    -0.68
    apple
    -0.68
    alid
    -0.68
    older
    -0.67
    POSITIVE LOGITS
     amounts
    0.99
     access
    0.94
     amount
    0.84
     quantities
    0.81
     unlimited
    0.80
     remission
    0.74
    itarian
    0.74
     mileage
    0.73
    urious
    0.69
     bandwidth
    0.68
    Activations Density 0.021%

    No Known Activations