© 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. 20795
    Prev
    Next
    INDEX
    Explanations

    phrases expressing wishes or gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or preference

    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
    ingen
    -0.75
    onut
    -0.71
    VERTISEMENT
    -0.71
    angular
    -0.69
    livious
    -0.69
    infeld
    -0.68
    cit
    -0.66
    lass
    -0.66
    illusion
    -0.66
    may
    -0.65
    POSITIVE LOGITS
     revenge
    0.81
    lihood
    0.77
    lier
    0.75
    liest
    0.71
     forgiveness
    0.70
     retribution
    0.70
     redress
    0.69
     predec
    0.68
     vengeance
    0.64
     warr
    0.64
    Activations Density 0.034%

    No Known Activations