Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8950
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "IG"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "IG" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wash
    -0.69
     Wash
    -0.68
     washing
    -0.67
     washed
    -0.67
     Tonight
    -0.66
     cond
    -0.64
     worsh
    -0.64
     entropy
    -0.63
     fares
    -0.61
    alist
    -0.60
    POSITIVE LOGITS
    IG
    4.21
    ig
    2.08
    igs
    1.68
     IG
    1.57
    IGN
    1.53
    IGH
    1.44
    IB
    1.40
    iga
    1.31
    OG
    1.30
    UG
    1.28
    Activations Density 0.011%

    No Known Activations