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. 3667
    Prev
    Next
    INDEX
    Explanations

    words or phrases with diacritical marks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a particular character or special symbol

    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
     capsule
    -0.69
     bomber
    -0.68
     Central
    -0.65
     calf
    -0.64
     Dallas
    -0.63
     paperback
    -0.62
     boosters
    -0.62
     Leviathan
    -0.61
     Cash
    -0.61
     narcotics
    -0.60
    POSITIVE LOGITS
    È
    4.73
    Ç
    1.36
    Ó
    1.13
    Ò
    1.13
    Ä
    1.12
     þ
    1.11
    Í
    1.10
    Æ
    1.08
    á¸
    1.02
    Ì
    1.02
    Activations Density 0.011%

    No Known Activations