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. 3293
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Caroline"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Caroline and Sil

    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
    akening
    -0.91
    awaru
    -0.84
    raising
    -0.82
    gettable
    -0.80
    riors
    -0.79
    unin
    -0.74
    arily
    -0.74
    ortality
    -0.69
    rior
    -0.67
    blance
    -0.67
    POSITIVE LOGITS
    lihood
    0.91
    icone
    0.90
    enced
    0.80
     Jav
    0.76
    bury
    0.73
    jad
    0.72
     Breed
    0.71
    ————
    0.68
    coni
    0.68
     Pour
    0.66
    Activations Density 0.043%

    No Known Activations