© 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. 0-RES-JB
    11. 519
    Prev
    Next
    INDEX
    Explanations

    terminology related to challenges, difficulties, hardships, and harsh realities

    oai_token-act-pair · gpt-3.5-turbo

    references to various challenging or harsh conditions and situations in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.80
     response
    -0.76
    osition
    -0.74
     indicator
    -0.72
    ée
    -0.70
    outine
    -0.69
    emark
    -0.68
     indication
    -0.68
     guess
    -0.67
    sey
    -0.67
    POSITIVE LOGITS
     difficulties
    2.03
     realities
    2.03
     dangers
    2.00
     evils
    1.90
     pitfalls
    1.88
     uncertainties
    1.80
     horrors
    1.77
     hardships
    1.76
     shortcomings
    1.73
     complexities
    1.72
    Activations Density 0.078%

    No Known Activations