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. 9092
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence or existence of various things

    oai_token-act-pair · gpt-3.5-turbo

    the concept of existence

    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
     Cotton
    -0.65
     hardest
    -0.60
     Pompe
    -0.57
    adding
    -0.57
    Iv
    -0.54
     tough
    -0.54
     toughest
    -0.54
     bowl
    -0.53
     bold
    -0.52
     regret
    -0.52
    POSITIVE LOGITS
     exists
    3.71
     existed
    2.88
     exist
    2.49
     survives
    1.81
     resides
    1.72
     arises
    1.71
     persists
    1.64
     occurs
    1.54
    existent
    1.47
     operates
    1.43
    Activations Density 0.016%

    No Known Activations