Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23117
    Prev
    Next
    INDEX
    Explanations

    instances of the word "EM" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    repeated references or mentions of the term "Em."

    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
     Kubrick
    -0.75
     Icelandic
    -0.70
     ASC
    -0.69
     Iceland
    -0.68
     Idle
    -0.67
    ãģį
    -0.65
     trout
    -0.63
     Elves
    -0.63
    aird
    -0.62
     Ancients
    -0.62
    POSITIVE LOGITS
    phasis
    1.42
    otional
    1.31
    otions
    1.30
    otion
    1.26
    brace
    1.22
    igrant
    1.21
    phas
    1.15
    igrants
    1.13
    issions
    1.12
    otive
    1.11
    Activations Density 0.017%

    No Known Activations