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. 10-RES-JB
    6. 14523
    Prev
    Next
    INDEX
    Explanations

    mentions of North and South Dakota, tribal lands, and specific Native American tribes

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and indigenous tribes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.85
     *)
    -0.80
     whilst
    -0.76
     realised
    -0.70
     organise
    -0.69
    oubted
    -0.67
     rumours
    -0.65
     realise
    -0.64
     [+
    -0.63
     Bulgar
    -0.63
    POSITIVE LOGITS
     nonprofit
    0.67
    Preview
    0.60
    avior
    0.57
    $.
    0.57
    stakes
    0.56
    +.
    0.56
     statewide
    0.56
    ashington
    0.54
     postseason
    0.54
    Americ
    0.54
    Activations Density 1.330%

    No Known Activations