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. 19101
    Prev
    Next
    INDEX
    Explanations

    the name "Mariano."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Luciano."

    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
    orative
    -0.81
    ivities
    -0.79
    places
    -0.68
    meet
    -0.68
    pse
    -0.67
    prising
    -0.66
    ERAL
    -0.63
    Ĵ
    -0.62
    iltr
    -0.62
     Ames
    -0.61
    POSITIVE LOGITS
    iano
    1.40
    iola
    0.93
    cia
    0.92
    ucci
    0.86
    orno
    0.86
    ido
    0.83
    io
    0.80
    ouf
    0.79
    iet
    0.79
     Ronaldo
    0.78
    Activations Density 0.007%

    No Known Activations