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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4613
    Prev
    Next
    INDEX
    Explanations

    instances of the word "evolve" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to growth and development

    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
     skim
    -0.78
     circ
    -0.75
     prost
    -0.74
    raq
    -0.73
     sweats
    -0.71
     scalp
    -0.69
    ocular
    -0.66
    orah
    -0.66
     lid
    -0.65
     vascular
    -0.63
    POSITIVE LOGITS
     evolve
    2.52
     evolves
    1.88
     evolving
    1.75
     Struggle
    1.32
     Pok
    0.98
     Planning
    0.95
    Poké
    0.93
     Breed
    0.92
     Push
    0.84
     Survive
    0.82
    Activations Density 0.035%

    No Known Activations