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. 3-RES-JB
    6. 13914
    Prev
    Next
    INDEX
    Explanations

    names containing the letters "Gh"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Ghalib."

    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
    payer
    -0.79
    eering
    -0.75
    eers
    -0.75
    nings
    -0.74
     stewards
    -0.72
    DOWN
    -0.71
     Galileo
    -0.67
    manship
    -0.66
    tenance
    -0.64
     Faust
    -0.64
    POSITIVE LOGITS
    ouls
    1.09
    ilst
    1.07
    irth
    1.00
    oses
    0.96
    angs
    0.93
    amel
    0.90
    adish
    0.90
    raq
    0.89
    afer
    0.89
    awar
    0.89
    Activations Density 0.009%

    No Known Activations