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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 13396
    Prev
    Next
    INDEX
    Explanations

    the surname "Nader" with varying levels of strength

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent individuals with the last name 'ader' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cess
    -0.78
    falls
    -0.66
    urses
    -0.65
     Gund
    -0.65
     Lent
    -0.63
    dogs
    -0.63
    KEY
    -0.63
    conn
    -0.62
    ivot
    -0.62
    inct
    -0.61
    POSITIVE LOGITS
    schild
    0.83
    */(
    0.79
    rang
    0.75
     Rebels
    0.71
    minist
    0.70
    unta
    0.70
    myra
    0.68
    aan
    0.68
    andom
    0.68
     Defin
    0.67
    Activations Density 0.036%

    No Known Activations