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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 10495
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individual or entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Em" and its variations, indicating a focus on individuals with that name

    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
     ASC
    -0.69
     overhead
    -0.66
    ãģį
    -0.66
     Kubrick
    -0.65
     Lovecraft
    -0.64
     numbered
    -0.64
     RIS
    -0.63
     sund
    -0.62
     hitherto
    -0.61
     draw
    -0.61
    POSITIVE LOGITS
    igrant
    1.24
    otional
    1.20
    igrants
    1.19
    otions
    1.19
    phasis
    1.18
    otion
    1.14
    brace
    1.13
    peror
    1.06
    manuel
    1.05
    blem
    1.04
    Activations Density 0.010%

    No Known Activations