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. 13717
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dwight"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Dwight" and its variations 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
    busters
    -0.74
    tale
    -0.74
    mented
    -0.72
    phies
    -0.72
    otech
    -0.71
    gra
    -0.71
    chant
    -0.71
    culosis
    -0.70
    smanship
    -0.70
    lia
    -0.69
    POSITIVE LOGITS
     ILCS
    0.78
     Shooter
    0.76
    oleon
    0.72
     Hots
    0.72
    éĹĺ
    0.69
     Schr
    0.69
     Peninsula
    0.67
    ackers
    0.66
     peninsula
    0.66
    EED
    0.66
    Activations Density 0.040%

    No Known Activations