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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 18049
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named Falk

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity named "Falk"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.90
    urger
    -0.81
    '>
    -0.69
     specificity
    -0.67
     Wonder
    -0.67
    oshop
    -0.67
    Mu
    -0.66
     Naruto
    -0.66
    Wonder
    -0.66
     Goku
    -0.66
    POSITIVE LOGITS
     Falk
    4.22
     Argent
    1.65
     Mald
    1.27
     Isle
    1.27
    LD
    1.23
     Cull
    1.18
     Hels
    1.17
     Ard
    1.16
     Vald
    1.13
    76561
    1.12
    Activations Density 0.046%

    No Known Activations