© 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. 9-RES-JB
    11. 18441
    Prev
    Next
    INDEX
    Explanations

    instances when people are visiting a place or showing up for various reasons

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TION
    -0.70
    going
    -0.67
     Continued
    -0.67
    ibles
    -0.65
    icularly
    -0.65
    resy
    -0.65
    quished
    -0.63
    Ability
    -0.63
    tymology
    -0.62
    pointers
    -0.61
    POSITIVE LOGITS
     reinforce
    1.11
     haunt
    1.04
     testify
    1.01
     relieve
    1.00
     investigate
    0.99
     meet
    0.99
     discuss
    0.95
     solve
    0.94
     join
    0.94
     bolster
    0.93
    Activations Density 0.225%

    No Known Activations