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. 27
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology projects and developments

    oai_token-act-pair · gpt-3.5-turbo

    elements related to the medical and pharmaceutical industry

    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
    ĸļ
    -0.81
    antage
    -0.77
     VIDEOS
    -0.76
    vironment
    -0.70
    VERTIS
    -0.64
     Lauder
    -0.63
     Azerbai
    -0.63
    ensional
    -0.62
     contrace
    -0.62
    javascript
    -0.62
    POSITIVE LOGITS
    tein
    0.90
    tarian
    0.75
    tarians
    0.75
    ombat
    0.74
    auld
    0.70
     Potion
    0.69
    export
    0.69
     Anonymous
    0.69
    iasco
    0.66
    andom
    0.66
    Activations Density 0.505%

    No Known Activations