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. 3506
    Prev
    Next
    INDEX
    Explanations

    instances or examples of specific scenarios or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific examples or cases in a discussion

    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
    ä½ľ
    -0.60
    hhhh
    -0.57
    reb
    -0.56
    finals
    -0.55
    nom
    -0.53
    allo
    -0.53
    it
    -0.53
    amaru
    -0.52
    wang
    -0.52
    âĢİ
    -0.52
    POSITIVE LOGITS
     instance
    3.92
     example
    2.42
    instance
    2.41
     instances
    2.29
    Instance
    1.55
    example
    1.54
     Example
    1.40
     examples
    1.19
    Example
    1.17
     Examples
    1.14
    Activations Density 0.017%

    No Known Activations