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. 9-RES-JB
    6. 4012
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and their political status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereof
    -0.77
    Specifically
    -0.76
     favors
    -0.73
     favored
    -0.71
     favoring
    -0.70
     utilizes
    -0.67
     utilizing
    -0.67
     labeled
    -0.66
     therein
    -0.66
     ______
    -0.65
    POSITIVE LOGITS
     inquest
    0.91
     paed
    0.88
    incial
    0.88
     counselling
    0.87
     Surrey
    0.86
    orkshire
    0.85
     apologise
    0.84
     Auckland
    0.84
     Yorkshire
    0.83
     apologised
    0.83
    Activations Density 1.996%

    No Known Activations