© 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. 20823
    Prev
    Next
    INDEX
    Explanations

    people's names and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific character sequences, particularly vowels and consonants in specific arrangements

    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
    nard
    -0.88
    shire
    -0.69
    rique
    -0.69
    kinson
    -0.67
    icals
    -0.67
    riers
    -0.67
    CLASSIFIED
    -0.67
    rican
    -0.66
    spect
    -0.66
    ICS
    -0.65
    POSITIVE LOGITS
    pper
    0.92
    inki
    0.89
    wi
    0.81
    atchewan
    0.76
    Ń·
    0.75
    lift
    0.74
    prus
    0.72
    hler
    0.72
     Helsinki
    0.71
    osta
    0.71
    Activations Density 0.067%

    No Known Activations