© 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. 10702
    Prev
    Next
    INDEX
    Explanations

    phrases related to an entity's role or function

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing the concept of "role" 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
    Ö
    -0.71
    phia
    -0.71
    >>\
    -0.70
    iken
    -0.69
    jad
    -0.68
    INESS
    -0.68
    clair
    -0.67
     Advocate
    -0.64
    itialized
    -0.63
    yd
    -0.61
    POSITIVE LOGITS
     antibodies
    0.75
     variables
    0.72
     Nanto
    0.70
     intermedi
    0.69
     elements
    0.69
    zyme
    0.68
     PACs
    0.68
     undue
    0.68
    unin
    0.67
     mater
    0.66
    Activations Density 0.182%

    No Known Activations