© 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. 6-RES-JB
    11. 11675
    Prev
    Next
    INDEX
    Explanations

    words related to identifying flaws or defects in technical systems

    oai_token-act-pair · gpt-3.5-turbo

    references to flaws and issues within systems or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.73
    ylum
    -0.71
     sidx
    -0.70
     boasting
    -0.66
     Refugees
    -0.66
     Millennials
    -0.65
    lees
    -0.65
     scorn
    -0.64
    holders
    -0.64
     refugees
    -0.63
    POSITIVE LOGITS
    tein
    0.88
     rudimentary
    0.73
     prost
    0.72
    wagen
    0.72
     math
    0.72
     delicate
    0.71
     technique
    0.70
     fundamentals
    0.70
     faulty
    0.69
     existing
    0.68
    Activations Density 0.503%

    No Known Activations