© 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. 7-RES-JB
    11. 23769
    Prev
    Next
    INDEX
    Explanations

    references to a particular aspect of a pancake-related topic

    oai_token-act-pair · gpt-3.5-turbo

    references to pancakes and associated names or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izations
    -0.77
    itatively
    -0.74
    ification
    -0.71
     Gleaming
    -0.68
    Ocean
    -0.67
     Supplemental
    -0.67
    âĵĺ
    -0.65
    grading
    -0.65
    ity
    -0.65
    ãģĨ
    -0.64
    POSITIVE LOGITS
    rase
    0.85
    nces
    0.84
    ingham
    0.82
    zanne
    0.78
    neys
    0.77
    eworks
    0.75
    rix
    0.74
    pton
    0.72
    rend
    0.71
    rians
    0.69
    Activations Density 0.085%

    No Known Activations