© 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. 9590
    Prev
    Next
    INDEX
    Explanations

    phrases signaling a conversational tone or indicating emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating acknowledgment or familiarity

    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
    utenberg
    -0.90
    stad
    -0.75
    omal
    -0.74
    iets
    -0.72
    otom
    -0.71
    aez
    -0.70
    OGR
    -0.70
    anmar
    -0.69
    isc
    -0.67
    pex
    -0.66
    POSITIVE LOGITS
    terday
    0.79
    lege
    0.76
     how
    0.71
     whats
    0.69
     WHAT
    0.67
    ledged
    0.67
     darn
    0.65
     what
    0.65
    abella
    0.64
     why
    0.63
    Activations Density 0.040%

    No Known Activations