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. 23113
    Prev
    Next
    INDEX
    Explanations

    words related to lack of knowledge or awareness, specifically focusing on the word "ignorant."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ignorance and lack of awareness

    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
    hetti
    -0.77
    ccording
    -0.73
    bourg
    -0.70
    gran
    -0.68
    ickr
    -0.68
    lished
    -0.66
    igsaw
    -0.65
    deen
    -0.65
    Textures
    -0.63
    emetery
    -0.62
    POSITIVE LOGITS
    ingly
    1.00
    ness
    0.90
    uania
    0.87
    ledge
    0.75
    lust
    0.75
    nesses
    0.74
     Leilan
    0.72
    äºĶ
    0.72
    lect
    0.71
    poke
    0.70
    Activations Density 0.030%

    No Known Activations