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. 6-RES-JB
    6. 17888
    Prev
    Next
    INDEX
    Explanations

    phrases related to items or concepts that are old or classic

    oai_token-act-pair · gpt-3.5-turbo

    references to vintage or antique items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lee
    -0.85
    hra
    -0.78
    ater
    -0.77
    olulu
    -0.76
    acles
    -0.75
    iant
    -0.72
    ermanent
    -0.72
    rawdownloadcloneembedreportprint
    -0.70
    ulty
    -0.70
    owitz
    -0.69
    POSITIVE LOGITS
    intage
    0.83
     1950
    0.77
     Revival
    0.75
     antique
    0.72
     Century
    0.70
    vre
    0.70
     fashioned
    0.69
     Manson
    0.68
     vintage
    0.67
     photographs
    0.66
    Activations Density 0.037%

    No Known Activations