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. 11680
    Prev
    Next
    INDEX
    Explanations

    proper names related to a specific person named "Evgen" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Gen" or relevant variations in the context of names or titles

    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
    *=-
    -0.77
    eneg
    -0.71
    ModLoader
    -0.65
     tradem
    -0.63
     redes
    -0.59
     hitch
    -0.59
    TPPStreamerBot
    -0.58
     estab
    -0.58
    ratom
    -0.57
    cffffcc
    -0.57
    POSITIVE LOGITS
    ocide
    1.42
    esis
    1.35
    furt
    1.21
    uine
    1.10
    ius
    0.97
    hardt
    0.95
    etics
    0.92
    iuses
    0.91
    etic
    0.89
    heim
    0.88
    Activations Density 0.009%

    No Known Activations