© 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. 8-RES-JB
    11. 20283
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "popularity" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 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
    erm
    -0.77
    INAL
    -0.73
    uran
    -0.73
     Dull
    -0.66
     intest
    -0.66
     Shell
    -0.65
     Fury
    -0.63
     Neurolog
    -0.61
    inis
    -0.61
    ¯¯¯¯
    -0.59
    POSITIVE LOGITS
    ately
    0.97
    ability
    0.90
    ously
    0.86
    Reviewer
    0.81
     quo
    0.76
    itious
    0.75
    itism
    0.73
    rise
    0.73
    uation
    0.71
    acy
    0.71
    Activations Density 0.038%

    No Known Activations