© 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. 20772
    Prev
    Next
    INDEX
    Explanations

    references to physical barriers or obstacles, such as barricades and walls

    oai_token-act-pair · gpt-3.5-turbo

    references to barriers or segregation

    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
    din
    -0.71
    NOR
    -0.68
    MIN
    -0.66
     americ
    -0.66
    gil
    -0.65
    WIN
    -0.63
     hemor
    -0.59
     negatively
    -0.58
     prosecut
    -0.57
    ICT
    -0.57
    POSITIVE LOGITS
    atural
    1.33
    et
    1.33
    eties
    1.30
    ets
    1.27
    ety
    1.25
    eness
    1.23
    etry
    1.20
    ements
    1.14
    estone
    1.12
    ete
    1.10
    Activations Density 0.123%

    No Known Activations