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. 4-RES-JB
    6. 18086
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to historical events, persons, and places

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and citations related to various entities or references

    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
    glers
    -0.47
    OIL
    -0.46
    emort
    -0.46
    Redd
    -0.43
     straw
    -0.43
    halla
    -0.42
    itialized
    -0.42
     hindsight
    -0.41
     Pixie
    -0.41
    Cause
    -0.41
    POSITIVE LOGITS
     respectively
    0.72
    etheless
    0.56
    ¥ŀ
    0.55
     dracon
    0.54
    acus
    0.49
    stellar
    0.48
    ç¥ŀ
    0.47
    lections
    0.46
     srf
    0.46
     latter
    0.46
    Activations Density 5.595%

    No Known Activations