© 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. 8-RES-JB
    11. 24494
    Prev
    Next
    INDEX
    Explanations

    instances of contrasting options or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that imply alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uay
    -0.89
    emouth
    -0.77
    onomy
    -0.73
    APTER
    -0.73
    °
    -0.72
    ¡
    -0.68
    oor
    -0.67
    ©
    -0.67
    ENE
    -0.65
    opia
    -0.65
    POSITIVE LOGITS
     alternatively
    1.16
     outright
    0.99
     else
    0.90
    Else
    0.89
    phans
    0.87
     simply
    0.84
    chard
    0.81
    acle
    0.79
     otherwise
    0.78
    chid
    0.77
    Activations Density 0.060%

    No Known Activations