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. 11884
    Prev
    Next
    INDEX
    Explanations

    instances of motion or direction in relation to travel or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direction or movement

    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
     Mub
    -0.77
    uzz
    -0.70
    rehens
    -0.70
    Percent
    -0.68
    sylvania
    -0.65
    ressor
    -0.64
    hma
    -0.62
     Corpus
    -0.61
    Mit
    -0.60
     Strat
    -0.60
    POSITIVE LOGITS
    heading
    1.03
     heading
    1.03
    canon
    0.87
    pins
    0.75
     adolesc
    0.74
     toward
    0.72
     Ahead
    0.71
     towards
    0.70
    ãĤĭ
    0.68
    daq
    0.68
    Activations Density 0.006%

    No Known Activations