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. 1-RES-JB
    6. 18359
    Prev
    Next
    INDEX
    Explanations

    references to the Royal Canadian Mounted Police (RCMP)

    oai_token-act-pair · gpt-3.5-turbo

    references to the RCMP (Royal Canadian Mounted Police)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bars
    -0.84
    piring
    -0.83
    title
    -0.82
    voc
    -0.81
    gets
    -0.80
    bos
    -0.79
    bar
    -0.79
    itia
    -0.79
    amus
    -0.79
    hab
    -0.77
    POSITIVE LOGITS
     RCMP
    1.21
     detachment
    0.96
     councill
    0.88
     adolesc
    0.85
     Constable
    0.84
     confir
    0.84
    avorite
    0.83
     mosqu
    0.82
     corrid
    0.81
     millenn
    0.80
    Activations Density 0.005%

    No Known Activations