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. 23702
    Prev
    Next
    INDEX
    Explanations

    references to adults

    oai_token-act-pair · gpt-3.5-turbo

    mentions of adults 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
    ãĥ¤
    -0.76
    adr
    -0.69
    Quotes
    -0.65
    atility
    -0.65
     Klux
    -0.65
     McDonnell
    -0.64
     Chandra
    -0.63
    Operation
    -0.63
    ī
    -0.63
    imoto
    -0.61
    POSITIVE LOGITS
     behaving
    0.91
    folk
    0.87
    maid
    0.84
     aged
    0.81
     who
    0.80
    erers
    0.78
     diapers
    0.77
    ager
    0.76
     alike
    0.74
     ages
    0.72
    Activations Density 0.012%

    No Known Activations