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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17431
    Prev
    Next
    INDEX
    Explanations

    specific numerical values followed by cities and monetary figures

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of numerical values or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arsen
    -0.69
     beaut
    -0.68
     respons
    -0.60
     proposition
    -0.59
     dedication
    -0.58
     dictator
    -0.57
     aside
    -0.56
     calendars
    -0.56
     liberation
    -0.56
     adventurer
    -0.55
    POSITIVE LOGITS
    5
    1.52
    0
    1.46
    8
    1.43
    3
    1.43
    6
    1.43
    9
    1.41
    7
    1.40
    2
    1.37
    4
    1.35
    1
    1.33
    Activations Density 0.052%

    No Known Activations