© 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. 4-RES-JB
    11. 2487
    Prev
    Next
    INDEX
    Explanations

    references to physical bells

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bell" in various contexts

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

    No Comments

    Negative Logits
     Agents
    -0.69
    selection
    -0.68
    VICE
    -0.68
    ©¶æ
    -0.68
    xual
    -0.68
    urat
    -0.67
    llers
    -0.67
    POR
    -0.66
    course
    -0.65
    esthesia
    -0.64
    POSITIVE LOGITS
    bell
    1.07
     bells
    1.05
    ows
    1.00
     bell
    0.89
    iod
    0.85
    ies
    0.84
     rang
    0.84
    owed
    0.83
     peppers
    0.82
    ossom
    0.82
    Activations Density 0.007%

    No Known Activations