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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 7734
    Prev
    Next
    INDEX
    Explanations

    endings indicating a form of closure or summary in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organised
    -0.85
     fanc
    -0.83
     organise
    -0.82
     hypnot
    -0.82
     farmland
    -0.80
     involuntary
    -0.79
     steady
    -0.78
     flattened
    -0.76
     recognised
    -0.75
     millenn
    -0.75
    POSITIVE LOGITS
    **
    1.52
    âĢ
    1.50
    «
    1.37
    âĸł
    1.37
    âĹı
    1.36
    îĢ
    1.34
     **
    1.34
    âĶ
    1.32
    */
    1.28
    âĢł
    1.28
    Activations Density 0.762%

    No Known Activations