© 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. 3973
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations and names

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations and terms related to disasters and emergency management

    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
    âĹ¼
    -0.73
     Aether
    -0.72
     Clever
    -0.72
    ucket
    -0.71
    uality
    -0.67
    utra
    -0.66
    het
    -0.65
    pocket
    -0.64
    cript
    -0.62
    ask
    -0.60
    POSITIVE LOGITS
    ruits
    0.97
     Fighters
    0.93
    iture
    0.87
    tails
    0.80
    enhagen
    0.79
    ruary
    0.78
    tailed
    0.77
    ishers
    0.77
    ãĤ©
    0.77
    rican
    0.76
    Activations Density 0.055%

    No Known Activations