Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23071
    Prev
    Next
    INDEX
    Explanations

    specific locations such as streets, islands, highways, and television networks

    oai_token-act-pair · gpt-3.5-turbo

    specific locations, places, or geographic references

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

    No Comments

    Negative Logits
    bra
    -0.68
     correction
    -0.68
    uctor
    -0.66
     redacted
    -0.65
    ortality
    -0.60
     blur
    -0.59
     braces
    -0.59
    uls
    -0.59
     brace
    -0.58
    oiler
    -0.58
    POSITIVE LOGITS
     occasions
    0.83
     doorstep
    0.83
     behalf
    0.82
     heels
    0.81
     basis
    0.77
    iatus
    0.76
     eve
    0.75
     periphery
    0.75
     occasion
    0.72
     shelf
    0.71
    Activations Density 0.372%

    No Known Activations