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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10067
    Prev
    Next
    INDEX
    Explanations

    references to the popularity of various entities or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    discussions about the concept of popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Neurolog
    -0.78
    erm
    -0.76
    ibur
    -0.74
    alk
    -0.71
    rib
    -0.70
    ¯¯
    -0.70
    thur
    -0.69
    endez
    -0.68
    beit
    -0.65
     Matter
    -0.64
    POSITIVE LOGITS
    popular
    0.88
     popularity
    0.88
    itism
    0.87
    yip
    0.80
    iqueness
    0.78
     ratings
    0.78
     ubiqu
    0.76
    é¾įå¥ij士
    0.72
     quiz
    0.70
    ately
    0.70
    Activations Density 0.012%

    No Known Activations