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. 11808
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "ran"

    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
    activation
    -0.72
    alty
    -0.72
    yet
    -0.71
    omical
    -0.71
    illusion
    -0.71
    olia
    -0.68
    ĨĴ
    -0.65
    rent
    -0.65
     Lauder
    -0.64
     maturity
    -0.63
    POSITIVE LOGITS
     Runner
    0.88
    swick
    0.87
     RUN
    0.86
     running
    0.77
    runner
    0.75
    running
    0.74
    Running
    0.73
    lasses
    0.73
    runners
    0.73
     runner
    0.73
    Activations Density 0.015%

    No Known Activations