© 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. 719
    Prev
    Next
    INDEX
    Explanations

    mentions of the initials "AG" followed by a single character or a single word

    oai_token-act-pair · gpt-3.5-turbo

    references to "AG" entities, likely indicating corporate or organizational mentions

    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
    dates
    -0.71
     stead
    -0.71
    phrine
    -0.68
    lights
    -0.67
    href
    -0.67
    neck
    -0.66
    Library
    -0.65
    lihood
    -0.65
    fixed
    -0.65
    around
    -0.65
    POSITIVE LOGITS
    reement
    1.04
    ENCY
    0.96
    reements
    0.89
    REE
    0.87
    glomer
    0.85
    HHHH
    0.81
    irlf
    0.81
    rowth
    0.80
    ates
    0.79
    rams
    0.79
    Activations Density 0.006%

    No Known Activations