© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    occurrences related to parades

    oai_token-act-pair · gpt-3.5-turbo

    mentions of parades

    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
    onom
    -0.80
    db
    -0.70
    Account
    -0.66
    Aff
    -0.66
    ogen
    -0.65
    BN
    -0.63
    IOR
    -0.63
    ben
    -0.63
    external
    -0.63
    RH
    -0.62
    POSITIVE LOGITS
     parade
    3.84
     Parade
    2.98
     procession
    2.09
     march
    1.67
     pageant
    1.37
     celebration
    1.27
     convoy
    1.22
     ceremony
    1.21
     festivities
    1.18
     celebrations
    1.17
    Activations Density 0.018%

    No Known Activations