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. 4-RES-JB
    6. 12719
    Prev
    Next
    INDEX
    Explanations

    proper names or titles related to Lud

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals named Lud and other related names

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

    No Comments

    Negative Logits
     Typhoon
    -0.75
    connected
    -0.72
    quished
    -0.70
    involved
    -0.68
    OTS
    -0.68
    =#
    -0.68
    ategory
    -0.67
    enfranch
    -0.64
    .............
    -0.64
     Reaction
    -0.64
    POSITIVE LOGITS
     Lud
    1.08
    sson
    0.92
     Matth
    0.88
     Koen
    0.74
    gement
    0.74
    uania
    0.74
    ĸļ
    0.73
     Hann
    0.68
     Von
    0.68
     Bam
    0.67
    Activations Density 0.015%

    No Known Activations