© 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. 11-RES-JB
    11. 1671
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing for email updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate calls to action or engagement prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesis
    -0.71
     recons
    -0.70
    */
    -0.64
    handedly
    -0.63
     disson
    -0.63
    âĶ
    -0.61
    dor
    -0.60
    FontSize
    -0.60
    eus
    -0.60
     experimentation
    -0.60
    POSITIVE LOGITS
    cloneembedreportprint
    0.92
     Liverpool
    0.90
     cele
    0.90
     Middles
    0.88
     daily
    0.87
     Started
    0.86
     Aston
    0.86
     Transcript
    0.83
     rugby
    0.83
     Everton
    0.81
    Activations Density 0.020%

    No Known Activations