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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 20171
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, Charlotte, with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Charlotte and its associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    algia
    -0.87
    culosis
    -0.85
    ially
    -0.74
    ulously
    -0.71
    flix
    -0.71
    alling
    -0.71
    ifact
    -0.70
    arial
    -0.70
    zai
    -0.68
    raid
    -0.66
    POSITIVE LOGITS
    otte
    1.28
     Hornets
    1.10
    ottesville
    1.07
    sburg
    1.02
     Charlotte
    0.86
    burg
    0.84
     Raleigh
    0.84
     Observer
    0.82
    issance
    0.79
    eston
    0.79
    Activations Density 0.034%

    No Known Activations