© 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. 11-RES-JB
    11. 2341
    Prev
    Next
    INDEX
    Explanations

    information about accomplishments, experiences, and personal characteristics of individuals

    oai_token-act-pair · gpt-3.5-turbo

    verb phrases indicating states of being or transitions experienced by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omial
    -0.84
     Ignore
    -0.69
     Pastebin
    -0.68
    ãĥ¯
    -0.68
    ÃŁ
    -0.67
     Contains
    -0.66
    allic
    -0.66
    ulence
    -0.66
     amplification
    -0.66
    shine
    -0.65
    POSITIVE LOGITS
     thrilled
    1.14
     fascinated
    1.11
     grateful
    1.10
     thankful
    1.10
     enrolled
    1.08
     restless
    1.07
     amazed
    1.07
     volunteering
    1.07
     ecstatic
    1.06
     intrigued
    1.06
    Activations Density 0.268%

    No Known Activations