© 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. 4-RES-JB
    11. 7200
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire for specific information or updates

    oai_token-act-pair · gpt-3.5-turbo

    requests and desires for information or updates

    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
    é¾
    -0.79
    EStreamFrame
    -0.77
    ä½ľ
    -0.73
    ãģ®å®
    -0.72
    displayText
    -0.70
    DAQ
    -0.70
    VEL
    -0.67
    ULT
    -0.67
    èĢ
    -0.64
    WAYS
    -0.64
    POSITIVE LOGITS
    gotten
    0.88
    hester
    0.84
    atoon
    0.82
    eri
    0.80
    ogh
    0.79
    ickets
    0.79
    ipeg
    0.76
    ever
    0.76
    onda
    0.75
    ledged
    0.72
    Activations Density 0.025%

    No Known Activations