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. 21050
    Prev
    Next
    INDEX
    Explanations

    phrases related to software updates or releases

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific release candidate labeled "RC" and related concepts

    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
    vre
    -0.77
     Horizon
    -0.75
     Spir
    -0.75
    iyah
    -0.68
    enz
    -0.67
     Mex
    -0.64
    uras
    -0.64
     Gladiator
    -0.64
    alse
    -0.64
    asses
    -0.62
    POSITIVE LOGITS
     RC
    2.03
    idered
    1.34
     novelty
    1.26
    corn
    1.22
    aroo
    1.11
    oso
    1.05
     replica
    1.03
     notwithstanding
    1.00
     ABS
    0.99
    eddy
    0.99
    Activations Density 0.046%

    No Known Activations