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. 8623
    Prev
    Next
    INDEX
    Explanations

    keywords related to questioning and inquiring about different kinds or types of things

    oai_token-act-pair · gpt-3.5-turbo

    inquiries related to purpose, role, and type of examples or categories

    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
    Interstitial
    -0.73
    vity
    -0.72
    hover
    -0.70
     Alive
    -0.67
    hern
    -0.63
    NetMessage
    -0.63
    naissance
    -0.63
    tesy
    -0.61
    tsky
    -0.61
     poppy
    -0.59
    POSITIVE LOGITS
    yip
    0.90
    soever
    0.87
     distinguishes
    0.74
     determines
    0.73
     happens
    0.73
    amac
    0.71
     transpired
    0.68
     differs
    0.67
    pires
    0.67
     defines
    0.65
    Activations Density 0.166%

    No Known Activations