© 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. 6-RES-JB
    11. 11940
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles or actions in social contexts, such as "learners," "contractors," and "servant leaders."

    oai_token-act-pair · gpt-3.5-turbo

    references to various roles and classifications of individuals or groups

    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
    nia
    -0.73
    osi
    -0.70
    ntax
    -0.67
    Untitled
    -0.67
    BUG
    -0.66
    Synopsis
    -0.63
    urrence
    -0.62
    aston
    -0.62
    osity
    -0.62
    asus
    -0.60
    POSITIVE LOGITS
    hips
    0.95
     themselves
    0.92
    mith
    0.90
    uggest
    0.89
    hip
    0.88
    ometimes
    0.83
    ensitive
    0.82
     ourselves
    0.81
    chool
    0.76
     extraord
    0.75
    Activations Density 0.230%

    No Known Activations