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. 11-RES-JB
    6. 8609
    Prev
    Next
    INDEX
    Explanations

    text encodings likely representing various data types or metadata within a larger body of content

    oai_token-act-pair · gpt-3.5-turbo

    instances of high numerical values or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.96
     metic
    -0.87
    ĸļ
    -0.86
     stem
    -0.86
     nerv
    -0.85
     smugglers
    -0.83
     Ceres
    -0.82
     tyr
    -0.80
     laure
    -0.78
     spiral
    -0.77
    POSITIVE LOGITS
    Examples
    1.47
    Use
    1.46
    Prov
    1.45
    Using
    1.45
    Performance
    1.44
    Ability
    1.43
    Similarly
    1.43
    Individual
    1.42
    Weak
    1.41
    Example
    1.41
    Activations Density 0.265%

    No Known Activations