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. 2-RES-JB
    6. 10149
    Prev
    Next
    INDEX
    Explanations

    mentions and references to the city of Paris

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Paris."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.80
    ownt
    -0.74
    served
    -0.74
    ULT
    -0.71
    ITH
    -0.70
    verbs
    -0.69
    onies
    -0.69
    uilt
    -0.69
    bish
    -0.69
    rama
    -0.67
    POSITIVE LOGITS
     Hilton
    1.07
    furt
    0.99
    ienne
    0.96
    mouth
    0.84
     Paris
    0.84
     Mé
    0.81
    etta
    0.81
     Attacks
    0.81
     Hebdo
    0.76
    agne
    0.75
    Activations Density 0.011%

    No Known Activations