© 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. 0-RES-JB
    11. 18011
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating a formal declaration or announcement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proclaim" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rig
    -0.72
     Uran
    -0.72
     NR
    -0.67
    uci
    -0.66
     compens
    -0.66
     sorting
    -0.66
     pool
    -0.65
     unused
    -0.65
    pool
    -0.65
     procedural
    -0.64
    POSITIVE LOGITS
     proclaimed
    2.84
     proclaim
    2.54
     proclaiming
    2.33
     proclamation
    1.96
     preached
    1.94
     preach
    1.77
     preaching
    1.63
     exclaim
    1.31
     exclaimed
    1.29
     trumpet
    1.22
    Activations Density 0.028%

    No Known Activations