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. 3-RES-JB
    6. 19035
    Prev
    Next
    INDEX
    Explanations

    references to the city of Rome

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Rome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intosh
    -1.17
    Marginal
    -0.96
    lasses
    -0.91
    merce
    -0.81
    TPPStreamerBot
    -0.80
    lished
    -0.78
    ramid
    -0.78
    pring
    -0.77
    iliary
    -0.75
    dash
    -0.75
    POSITIVE LOGITS
     Pact
    0.92
    anus
    0.82
     Inquisition
    0.77
     Reign
    0.74
     Rome
    0.73
     Mysteries
    0.73
    senal
    0.72
     Circus
    0.71
    ophobia
    0.70
     Antiqu
    0.69
    Activations Density 0.006%

    No Known Activations