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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5464
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of self-awareness and introspection

    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
     respectively
    -0.68
     themselves
    -0.65
    EMS
    -0.61
     apiece
    -0.58
     Diff
    -0.51
     Trident
    -0.51
    arettes
    -0.51
    idates
    -0.51
     Belarus
    -0.50
     Canaveral
    -0.49
    POSITIVE LOGITS
     myself
    1.32
     my
    0.82
    poke
    0.79
    oan
    0.68
     personally
    0.67
    eah
    0.65
     writing
    0.61
    ograp
    0.58
     <+
    0.57
    cffff
    0.56
    Activations Density 0.780%

    No Known Activations