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. 11-RES-JB
    6. 8567
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period followed by a paragraph break (Ċ) and potentially other special characters

    oai_token-act-pair · gpt-3.5-turbo

    indicative phrases that suggest uncertainty or concern in a situation

    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
     citiz
    -0.83
    ¥ŀ
    -0.80
     princ
    -0.79
     ende
    -0.78
     oun
    -0.76
    aditional
    -0.74
     commissions
    -0.74
     prosec
    -0.73
     eleph
    -0.73
    ortunately
    -0.73
    POSITIVE LOGITS
    "[
    2.24
    "
    2.13
    "(
    2.11
    "'
    1.95
    "...
    1.81
    He
    1.76
    "â̦
    1.70
    Asked
    1.62
    "-
    1.61
    SPONSORED
    1.56
    Activations Density 0.462%

    No Known Activations