© 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. 9-RES-JB
    11. 7401
    Prev
    Next
    INDEX
    Explanations

    mentions of recommendations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recommendations and suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophon
    -0.79
    arton
    -0.73
    zona
    -0.73
    inside
    -0.68
     Brus
    -0.67
    fare
    -0.66
    adelphia
    -0.64
    Ï
    -0.64
    ipel
    -0.63
    bre
    -0.63
    POSITIVE LOGITS
    Recommend
    0.89
     recommendations
    0.84
     recommendation
    0.78
     recommending
    0.77
     guidelines
    0.77
     guideline
    0.70
     Guidelines
    0.70
     recommended
    0.70
     criteria
    0.70
    recomm
    0.69
    Activations Density 0.054%

    No Known Activations