© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3300
    Prev
    Next
    INDEX
    Explanations

    words related to proving or showing strong evidence or capability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proving" and its variations, indicating the action of demonstrating or establishing something as true

    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
    overed
    -0.62
    ussed
    -0.61
    pora
    -0.60
    inis
    -0.59
    ropri
    -0.59
    agan
    -0.59
     newsletters
    -0.58
     Peninsula
    -0.57
    olly
    -0.57
    oho
    -0.57
    POSITIVE LOGITS
     proving
    0.98
    ãĤ¤ãĥĪ
    0.91
     proves
    0.90
     prove
    0.82
    GGGGGGGG
    0.78
     dispro
    0.77
     proved
    0.77
    iary
    0.76
    =>
    0.73
    ãĤ©
    0.72
    Activations Density 0.003%

    No Known Activations