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. 3-RES-JB
    6. 14832
    Prev
    Next
    INDEX
    Explanations

    words related to pursuing or chasing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "chase" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    animous
    -0.84
    acies
    -0.76
    aston
    -0.72
    itcher
    -0.72
    rogens
    -0.70
    itent
    -0.70
    emetery
    -0.69
    osate
    -0.69
    ionic
    -0.68
    itutional
    -0.68
    POSITIVE LOGITS
     chase
    1.01
     chasing
    0.84
    eers
    0.80
     pursu
    0.74
     Crusade
    0.73
    backs
    0.72
    cade
    0.71
    crow
    0.70
    ============
    0.69
    âĸ¬
    0.68
    Activations Density 0.013%

    No Known Activations