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. 0-RES-JB
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    the concept of something being permanent

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of permanence

    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
    zen
    -0.72
    fort
    -0.71
    oft
    -0.71
    hoe
    -0.70
    plot
    -0.68
    axter
    -0.67
    math
    -0.65
    RPG
    -0.65
    ook
    -0.64
    Edge
    -0.64
    POSITIVE LOGITS
     permanent
    3.77
     Permanent
    2.55
    ermanent
    2.27
     temporary
    2.10
     permanently
    2.08
     perman
    1.89
    manent
    1.84
     irreversible
    1.49
     Temporary
    1.45
     perpetual
    1.39
    Activations Density 0.008%

    No Known Activations