© 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. 10855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start of a list or point

    oai_token-act-pair · gpt-3.5-turbo

    the word "let's" and its variations or contexts suggesting a call to action

    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
    eur
    -0.73
    ELD
    -0.66
     Source
    -0.64
     Citiz
    -0.63
     Allied
    -0.60
    Creat
    -0.60
     Range
    -0.58
     Able
    -0.58
     Slug
    -0.56
     Associated
    -0.55
    POSITIVE LOGITS
     pretend
    0.95
     assume
    0.92
     clarify
    0.88
     gaze
    0.88
     proceed
    0.87
     presume
    0.85
    iblings
    0.84
     suppose
    0.83
     continue
    0.83
     beware
    0.83
    Activations Density 0.016%

    No Known Activations