© 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. 20638
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing collective opinions or observations

    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
    forms
    -0.67
    REDACTED
    -0.63
    aults
    -0.60
     Glory
    -0.58
    ulence
    -0.56
    rocket
    -0.56
    accompan
    -0.54
     Romance
    -0.53
    à
    -0.51
    Reloaded
    -0.51
    POSITIVE LOGITS
    akening
    1.28
    're
    1.21
    've
    1.09
     need
    1.02
    akens
    1.02
    ighed
    1.01
     shouldn
    0.97
     believe
    0.96
     anticipate
    0.94
     haven
    0.91
    Activations Density 0.197%

    No Known Activations