© 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. 7022
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms starting with 'IM'

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "IM" 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
    yards
    -0.85
    NetMessage
    -0.70
    halla
    -0.67
     Caller
    -0.65
     Thames
    -0.64
     mars
    -0.64
    hma
    -0.62
     grease
    -0.61
    \\\\\\\\
    -0.61
    naire
    -0.60
    POSITIVE LOGITS
    PLE
    1.13
    MY
    1.08
    MED
    1.02
    ITED
    1.01
    HO
    1.00
    MER
    1.00
    bledon
    0.99
    ple
    0.98
    pson
    0.97
    PLIC
    0.95
    Activations Density 0.010%

    No Known Activations