Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 6762
    Prev
    Next
    INDEX
    Explanations

    phrases related to contracts and deals

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating actions or descriptors related to entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.76
    united
    -0.68
    erb
    -0.64
    orce
    -0.64
    riend
    -0.63
    jar
    -0.63
    isphere
    -0.63
     selves
    -0.62
    few
    -0.61
    gem
    -0.60
    POSITIVE LOGITS
     unspecified
    0.91
     an
    0.89
     a
    0.83
     another
    0.68
     Class
    0.67
     lieu
    0.64
     preliminary
    0.64
     undisclosed
    0.64
     prelim
    0.62
     approximately
    0.62
    Activations Density 0.329%

    No Known Activations