Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17488
    Prev
    Next
    INDEX
    Explanations

    references to lacking something or insufficiency

    oai_token-act-pair · gpt-3.5-turbo

    words indicating a lack or deficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shot
    -0.73
    OPLE
    -0.72
    ricks
    -0.68
    Dialogue
    -0.65
     bulls
    -0.62
    Kent
    -0.62
    Args
    -0.60
    Roll
    -0.60
    hedon
    -0.60
    hesis
    -0.59
    POSITIVE LOGITS
    luster
    1.26
    ateral
    0.95
    uminati
    0.79
    ppe
    0.72
    omore
    0.71
    utenant
    0.70
    emonic
    0.69
     footing
    0.69
    nesses
    0.68
    warm
    0.67
    Activations Density 0.028%

    No Known Activations