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. 8-RES-JB
    6. 22093
    Prev
    Next
    INDEX
    Explanations

    paragraphs or sentences with the phrase "we must also address the elephant in the room."

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that are organized and formatted, possibly indicating structure or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.75
     prec
    -0.73
     estab
    -0.72
     seiz
    -0.71
     skelet
    -0.71
     rightful
    -0.68
     dismant
    -0.67
     beh
    -0.67
     symb
    -0.66
     ba
    -0.65
    POSITIVE LOGITS
    Introduction
    1.40
    Welcome
    1.31
    Published
    1.29
    Disclaimer
    1.26
    Contents
    1.23
    Whether
    1.22
    This
    1.21
    Guest
    1.21
    When
    1.21
    Recent
    1.20
    Activations Density 0.194%

    No Known Activations