© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 4993
    Prev
    Next
    INDEX
    Explanations

    specific characters (such as 'Ċ' and 'âĢ') that are consistent within the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and numerical data related to economic statistics

    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
     prosec
    -0.85
     sil
    -0.83
     holog
    -0.83
     sculpt
    -0.82
     describ
    -0.81
     reneg
    -0.80
     endeav
    -0.79
     deton
    -0.79
     shielded
    -0.78
     dynam
    -0.77
    POSITIVE LOGITS
    Overall
    1.87
    Percent
    1.78
    Average
    1.78
    Among
    1.76
    Compared
    1.69
    Across
    1.68
    Of
    1.60
    Interestingly
    1.59
    According
    1.58
    Nearly
    1.58
    Activations Density 0.296%

    No Known Activations