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. 6-RES-JB
    6. 22346
    Prev
    Next
    INDEX
    Explanations

    geographical locations such as towns, cities, municipalities, counties, and villages

    oai_token-act-pair · gpt-3.5-turbo

    references to towns and municipalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.63
    PUT
    -0.63
    OUT
    -0.62
    --+
    -0.62
     agent
    -0.60
     STA
    -0.60
     Submission
    -0.60
    potion
    -0.59
    Agent
    -0.59
     induction
    -0.59
    POSITIVE LOGITS
    hips
    1.46
    chool
    1.17
    folk
    1.09
    hare
    0.97
     valleys
    0.92
    hip
    0.91
     bordering
    0.90
     counties
    0.89
    worn
    0.88
     regions
    0.84
    Activations Density 0.097%

    No Known Activations