© 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. 0-RES-JB
    11. 8314
    Prev
    Next
    INDEX
    Explanations

    references to subscription services or payment plans

    oai_token-act-pair · gpt-3.5-turbo

    references to subscription-based services

    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
     spac
    -0.67
    Hom
    -0.66
    lam
    -0.66
     Height
    -0.65
     Hait
    -0.65
     Bush
    -0.65
     Vill
    -0.64
    ese
    -0.63
     Gill
    -0.63
    ev
    -0.63
    POSITIVE LOGITS
     subscription
    3.78
     subscriptions
    3.04
     subscriber
    2.02
     subscribers
    1.96
     subscribed
    1.83
     subscribe
    1.70
     subscribing
    1.64
    scription
    1.58
     membership
    1.51
     subscrib
    1.47
    Activations Density 0.011%

    No Known Activations