© 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. 18554
    Prev
    Next
    INDEX
    Explanations

    phrases discussing opinions, accusations, or statements made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "also."

    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
    Stack
    -0.76
    acious
    -0.66
    Bind
    -0.65
     Ange
    -0.64
    jam
    -0.63
    agus
    -0.62
    animate
    -0.62
     Replacement
    -0.62
     Reincarn
    -0.61
    stack
    -0.61
    POSITIVE LOGITS
     includes
    0.85
     anecd
    0.82
     cautioned
    0.82
     included
    0.81
     consulted
    0.78
     noteworthy
    0.78
     contributed
    0.77
     optionally
    0.76
     discussed
    0.76
     includ
    0.75
    Activations Density 0.109%

    No Known Activations