© 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. 4-RES-JB
    11. 24208
    Prev
    Next
    INDEX
    Explanations

    references to the education and well-being of young children

    oai_token-act-pair · gpt-3.5-turbo

    references to children or related terms

    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
    rawdownloadcloneembedreportprint
    -0.82
    issan
    -0.74
    ked
    -0.66
    ModLoader
    -0.62
    pmwiki
    -0.62
    undy
    -0.61
    ced
    -0.61
    rontal
    -0.61
    daq
    -0.60
    lled
    -0.60
    POSITIVE LOGITS
     enrolled
    0.83
    children
    0.81
    riages
    0.79
    lings
    0.79
     aged
    0.73
     orphans
    0.68
    arten
    0.68
     who
    0.67
    child
    0.66
     diagnosed
    0.65
    Activations Density 0.092%

    No Known Activations