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. 11-RES-JB
    6. 18941
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and financial numbers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and percentages

    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
     brill
    -1.04
     cloning
    -0.92
    ikuman
    -0.82
     enthusi
    -0.81
     diamond
    -0.79
     glim
    -0.78
    yip
    -0.76
     tyr
    -0.75
     rubbish
    -0.75
     mate
    -0.75
    POSITIVE LOGITS
    âĢ
    1.63
    âĢł
    1.39
    âģ
    1.30
     Moreover
    1.26
     âĢ
    1.24
    Moreover
    1.21
    ¶
    1.20
     Nonetheless
    1.19
     Indeed
    1.18
    Yet
    1.18
    Activations Density 0.371%

    No Known Activations