Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7727
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements expressing surprise, frustration, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or emphasis using the word "hell"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Decre
    -0.75
    士
    -0.72
    States
    -0.72
    Short
    -0.72
    Random
    -0.72
    Population
    -0.71
    Recomm
    -0.71
    Vert
    -0.70
     Surveillance
    -0.69
    APD
    -0.69
    POSITIVE LOGITS
    enic
    1.05
    ishly
    1.02
    hole
    0.91
    oise
    0.89
    holes
    0.88
    urous
    0.85
    fuck
    0.82
    dump
    0.82
    aciously
    0.81
    hound
    0.81
    Activations Density 0.009%

    No Known Activations