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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23442
    Prev
    Next
    INDEX
    Explanations

    adverbs that emphasize the extremity or completeness of an action or quality

    oai_token-act-pair · gpt-3.5-turbo

    the usage of "virtually" and "practically" to indicate near-totality or approximation

    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
    esan
    -0.69
    tv
    -0.62
     Explan
    -0.62
    hur
    -0.61
    answer
    -0.60
     Cly
    -0.60
    ikk
    -0.59
    "},{"
    -0.58
    er
    -0.57
    fix
    -0.57
    POSITIVE LOGITS
     virtually
    2.94
     practically
    2.12
     almost
    1.70
     essentially
    1.54
     remarkably
    1.44
     scarcely
    1.43
    almost
    1.43
     nearly
    1.43
     basically
    1.36
     vastly
    1.30
    Activations Density 0.009%

    No Known Activations