© 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. 9618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal ability or capacity

    oai_token-act-pair · gpt-3.5-turbo

    the word "can" and its variations indicating capability or possibility

    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
     rejection
    -0.64
     revision
    -0.61
     Federation
    -0.61
     rejected
    -0.61
     Rising
    -0.59
     Hunters
    -0.59
     vacated
    -0.57
     striving
    -0.56
    roid
    -0.56
     Strikes
    -0.55
    POSITIVE LOGITS
    't
    1.73
    berra
    1.13
    adian
    1.12
    NOT
    1.06
    isters
    0.98
     tell
    0.87
     afford
    0.87
     attest
    0.86
     easily
    0.86
    tera
    0.85
    Activations Density 0.159%

    No Known Activations