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. 1-RES-JB
    6. 12080
    Prev
    Next
    INDEX
    Explanations

    the word "none" occurring frequently in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "none" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.38
    ĵĺ
    -0.29
     WATCHED
    -0.28
     Mages
    -0.28
     Pwr
    -0.28
    ongyang
    -0.28
    bard
    -0.27
    natureconservancy
    -0.26
     Fighters
    -0.26
     Sear
    -0.26
    POSITIVE LOGITS
    ividual
    0.33
     onward
    0.33
    okane
    0.32
    ierre
    0.31
    idth
    0.31
     lasted
    0.30
    iazep
    0.30
     vou
    0.29
    uart
    0.29
    gins
    0.29
    Activations Density 1.439%

    No Known Activations