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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2742
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, especially those starting with 'An'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "An" in various contexts

    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
    BOOK
    -0.66
    è¯
    -0.66
     pupils
    -0.63
    âĸº
    -0.63
     mayors
    -0.62
     Bulg
    -0.62
     Pry
    -0.61
     âĸĪ
    -0.61
     Lyndon
    -0.61
     scares
    -0.60
    POSITIVE LOGITS
    omaly
    1.30
    alogue
    1.21
    alys
    1.15
    ubis
    1.13
    omal
    1.12
    terior
    1.09
    alyses
    1.07
    akin
    1.03
    esthetic
    1.03
    notation
    1.02
    Activations Density 0.023%

    No Known Activations