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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word 'bakers'

    oai_token-act-pair · gpt-3.5-turbo

    references to "makers" or people involved in production or creation

    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
     Reconstruction
    -0.69
     Pesh
    -0.68
    âĸ¬
    -0.67
     Territories
    -0.66
     bilateral
    -0.64
     monarchy
    -0.64
     Railway
    -0.64
     malaria
    -0.62
     Canad
    -0.62
     dissolution
    -0.61
    POSITIVE LOGITS
    paces
    1.16
    ervatives
    1.15
    cript
    1.11
    chool
    1.07
    pace
    1.06
    ucker
    1.04
    ervative
    1.04
    linger
    1.04
    pread
    1.02
    ynthesis
    0.99
    Activations Density 0.011%

    No Known Activations