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. 17535
    Prev
    Next
    INDEX
    Explanations

    male first names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and places

    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
     lightly
    -0.57
     âĸ
    -0.56
     lockdown
    -0.55
     nutshell
    -0.54
    OPLE
    -0.53
     à¨
    -0.53
    ãĤ¼ãĤ¦ãĤ¹
    -0.52
     Democr
    -0.52
     pleas
    -0.51
    DragonMagazine
    -0.51
    POSITIVE LOGITS
    ona
    0.83
    zes
    0.71
    avia
    0.67
    ola
    0.65
    ys
    0.63
    atus
    0.62
    ewater
    0.62
    zen
    0.61
    azz
    0.60
    razen
    0.60
    Activations Density 0.575%

    No Known Activations