© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7452
    Prev
    Next
    INDEX
    Explanations

    references to subscribers in a digital context

    oai_token-act-pair · gpt-3.5-turbo

    references to subscribers or subscription metrics

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

    No Comments

    Negative Logits
    ball
    -0.69
     Pist
    -0.68
     Zurich
    -0.66
     Peninsula
    -0.64
    ofi
    -0.63
     Messi
    -0.62
     Obst
    -0.62
    Chain
    -0.62
    enegger
    -0.62
     Horror
    -0.60
    POSITIVE LOGITS
     subscribers
    1.17
     subscriber
    1.08
    hip
    1.05
     subscriptions
    0.92
     Unlimited
    0.91
     subscription
    0.85
    scrib
    0.84
    riber
    0.78
    umbnails
    0.76
    iosity
    0.75
    Activations Density 0.007%

    No Known Activations