© 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 EvalsExportsAPI 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. 10563
    Prev
    Next
    INDEX
    Explanations

    reasons or motivations behind actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions that indicate reasons or purposes

    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
     oneself
    -0.87
    vier
    -0.82
    ratulations
    -0.73
     yourselves
    -0.71
    uilt
    -0.70
    ashtra
    -0.69
    baum
    -0.67
    auld
    -0.67
    ower
    -0.66
    orer
    -0.65
    POSITIVE LOGITS
     glory
    0.74
     hers
    0.64
     acquisitions
    0.62
     Wonderland
    0.62
     counterparts
    0.60
    ãĥ¯
    0.59
     persuasion
    0.59
    stood
    0.59
     mates
    0.58
    venge
    0.57
    Activations Density 0.441%

    No Known Activations