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. 10-RES-JB
    6. 620
    Prev
    Next
    INDEX
    Explanations

    technical terms and expressions related to specifications and instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and discussions around governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Secondly
    -0.93
     secondly
    -0.92
     Secondly
    -0.88
     Whilst
    -0.85
    ''.
    -0.78
     Reply
    -0.78
    "]=>
    -0.78
    ãĢį
    -0.72
     âĸº
    -0.71
    notations
    -0.70
    POSITIVE LOGITS
    fitted
    0.68
     sprawling
    0.62
     centerpiece
    0.60
     stockp
    0.59
     nonprofit
    0.57
     surg
    0.57
     garg
    0.57
     giant
    0.57
     legions
    0.56
     billions
    0.56
    Activations Density 1.089%

    No Known Activations