© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23166
    Prev
    Next
    INDEX
    Explanations

    terms related to criticism or negative evaluation, focusing on phrases like "flawed" or "faulty"

    oai_token-act-pair · gpt-3.5-turbo

    references to flawed or imperfect systems and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.85
    ista
    -0.75
    ILA
    -0.74
    olon
    -0.71
    arya
    -0.71
    Shop
    -0.71
    ilet
    -0.70
    iser
    -0.69
    ectar
    -0.69
    arger
    -0.69
    POSITIVE LOGITS
     flawed
    0.93
     compromises
    0.83
     flaw
    0.79
     undermin
    0.78
     guiActiveUn
    0.78
     flaws
    0.76
     caric
    0.76
     oversight
    0.71
     interpretations
    0.69
     assumptions
    0.69
    Activations Density 0.016%

    No Known Activations