© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12982
    Prev
    Next
    INDEX
    Explanations

    the word "podium"

    oai_token-act-pair · gpt-3.5-turbo

    references to podiums and speaking engagements

    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
     Disease
    -0.69
    Operation
    -0.68
     Sins
    -0.65
     Mut
    -0.64
    version
    -0.62
     Flesh
    -0.61
    ay
    -0.61
    sin
    -0.61
    Allen
    -0.60
    Scan
    -0.60
    POSITIVE LOGITS
     podium
    4.09
     microphone
    1.38
     pedest
    1.34
     lect
    1.25
     throne
    1.15
     scoreboard
    1.12
     microphones
    1.09
     lapt
    1.07
     stage
    1.06
     pole
    1.06
    Activations Density 0.015%

    No Known Activations