© 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. 11191
    Prev
    Next
    INDEX
    Explanations

    phrases or statements indicating awareness or description of ongoing events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing states of being or occurrences in past and present tenses

    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
    sted
    -0.67
     DOI
    -0.62
     Disaster
    -0.57
    mon
    -0.57
     Dickinson
    -0.57
    vale
    -0.57
    oples
    -0.55
    hement
    -0.55
    Shape
    -0.54
    velt
    -0.53
    POSITIVE LOGITS
     happening
    1.52
     occurring
    1.16
     transpired
    1.02
     going
    1.01
     unfolding
    0.98
     achievable
    0.98
     bothering
    0.95
     happ
    0.92
     motivating
    0.90
     happened
    0.89
    Activations Density 0.086%

    No Known Activations