© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7009
    Prev
    Next
    INDEX
    Explanations

    words related to physical measurements, such as depth

    oai_token-act-pair · gpt-3.5-turbo

    references to 'depth' in various contexts

    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
    eer
    -0.92
    jee
    -0.91
    eers
    -0.83
    RY
    -0.67
    immune
    -0.67
    rote
    -0.67
     Sabha
    -0.66
    iggs
    -0.64
    ifiable
    -0.64
    ronic
    -0.63
    POSITIVE LOGITS
     perception
    0.87
     depth
    0.81
     penetration
    0.80
    hole
    0.79
    chart
    0.74
     depths
    0.73
     Depth
    0.72
    plings
    0.70
    holes
    0.70
     dug
    0.69
    Activations Density 0.031%

    No Known Activations