© 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. 8-RES-JB
    11. 3178
    Prev
    Next
    INDEX
    Explanations

    proper nouns with quotation marks around them

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ļ½
    -0.96
    ĻĤ
    -0.80
    ¿
    -0.78
    ¾
    -0.76
    ailing
    -0.74
    aults
    -0.73
    stant
    -0.70
    ¸
    -0.70
    ousse
    -0.68
    ushi
    -0.67
    POSITIVE LOGITS
    /"
    1.35
     moniker
    0.89
     appell
    0.76
     designation
    0.74
     aka
    0.74
     mantra
    0.71
     motto
    0.71
     label
    0.70
     mentality
    0.69
     ("
    0.68
    Activations Density 0.102%

    No Known Activations