© 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. 4-RES-JB
    11. 14920
    Prev
    Next
    INDEX
    Explanations

    technical or military related terms and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    words that pertain to various forms of "raising" or "increasing."

    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
    papers
    -0.84
    eries
    -0.74
    osponsors
    -0.72
    arious
    -0.69
    icter
    -0.67
    mission
    -0.65
    olls
    -0.65
     earthqu
    -0.65
    ockets
    -0.65
    obb
    -0.65
    POSITIVE LOGITS
     Parenthood
    1.14
    xual
    0.96
    hift
    0.73
    ========
    0.73
     Sap
    0.70
    rah
    0.68
     Gaal
    0.68
     partName
    0.67
     Sadd
    0.65
     Ones
    0.63
    Activations Density 0.014%

    No Known Activations