© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12271
    Prev
    Next
    INDEX
    Explanations

    words related to various topics and events, potentially including politics, sports, and organizational activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to records and achievements

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

    No Comments

    Negative Logits
    ttes
    -0.79
    issance
    -0.71
    Ͻ
    -0.70
    apons
    -0.68
     Pigs
    -0.65
    agine
    -0.65
    istle
    -0.63
    orthy
    -0.63
     Architects
    -0.62
     horm
    -0.62
    POSITIVE LOGITS
    Sensor
    0.93
    ONSORED
    0.85
    Related
    0.76
    Article
    0.74
    Tags
    0.73
    SPONSORED
    0.73
     Caption
    0.72
    Push
    0.70
    Fra
    0.69
    credit
    0.68
    Activations Density 0.265%

    No Known Activations