© 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. 1-RES-JB
    11. 20333
    Prev
    Next
    INDEX
    Explanations

    words related to bells and names or locations that include "bell."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bell"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ãľ
    -0.67
     Forth
    -0.65
     Spac
    -0.61
     unpre
    -0.60
     DUI
    -0.60
    EEE
    -0.59
     Folk
    -0.59
    employment
    -0.58
     Freak
    -0.58
    ggies
    -0.58
    POSITIVE LOGITS
    bell
    1.66
    otine
    0.93
     corrid
    0.92
    iola
    0.91
     bells
    0.88
     destro
    0.85
    ows
    0.84
    south
    0.84
    itude
    0.80
     rul
    0.80
    Activations Density 0.004%

    No Known Activations