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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10278
    Prev
    Next
    INDEX
    Explanations

    words related to nuclear power plants or technical terms within various fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nuclear energy and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     channels
    -0.66
     pillars
    -0.65
     avenues
    -0.64
     bins
    -0.64
     fixtures
    -0.64
     priorities
    -0.64
     divisions
    -0.62
    ooks
    -0.62
     departments
    -0.62
    headers
    -0.62
    POSITIVE LOGITS
    robe
    0.84
     or
    0.81
    ifier
    0.80
    chuk
    0.80
    ogram
    0.78
    .–
    0.77
    ographer
    0.76
     anywhere
    0.75
    uble
    0.75
     someday
    0.73
    Activations Density 0.453%

    No Known Activations