© 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. 21176
    Prev
    Next
    INDEX
    Explanations

    references to default settings or values

    oai_token-act-pair · gpt-3.5-turbo

    references to default settings or configurations

    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
    borough
    -0.90
    asant
    -0.73
    wife
    -0.71
    rums
    -0.70
    asus
    -0.68
    hemat
    -0.67
    crow
    -0.66
    ales
    -0.66
    EAR
    -0.64
    chers
    -0.64
    POSITIVE LOGITS
     settings
    1.08
     behaviour
    0.92
     behavior
    0.88
     gateway
    0.88
     setting
    0.83
    dict
    0.82
     values
    0.80
    ed
    0.79
     configuration
    0.78
     Settings
    0.78
    Activations Density 0.030%

    No Known Activations