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. 22158
    Prev
    Next
    INDEX
    Explanations

    mentions of inadequacy, insufficiency, or not meeting requirements in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inadequacy 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
    dar
    -0.81
    cow
    -0.77
    aptic
    -0.76
    dot
    -0.72
    da
    -0.70
    saw
    -0.70
    âĸ¬
    -0.70
    =-=-=-=-
    -0.69
    =-=-=-=-=-=-=-=-
    -0.68
    76561
    -0.68
    POSITIVE LOGITS
    mble
    0.86
    intendent
    0.84
    ufficient
    0.83
     accommodations
    0.79
     remed
    0.79
     adequate
    0.78
     accommodation
    0.77
     adequately
    0.77
    adequ
    0.76
     adequ
    0.76
    Activations Density 0.021%

    No Known Activations