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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17406
    Prev
    Next
    INDEX
    Explanations

    references to proper nouns (names) related to the name "Dick"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Dick" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.77
    kees
    -0.76
     srf
    -0.74
    ccording
    -0.69
    yip
    -0.66
     Carbuncle
    -0.65
     adversity
    -0.64
     waters
    -0.64
     tradem
    -0.64
     Aval
    -0.64
    POSITIVE LOGITS
    enson
    1.02
     Cheney
    0.98
    erson
    0.93
    ible
    0.90
    ie
    0.85
    inson
    0.84
     Grayson
    0.84
    buster
    0.83
    inges
    0.80
    stein
    0.80
    Activations Density 0.014%

    No Known Activations