© 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. 362
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of storms and their impacts

    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
    ibaba
    -0.95
     knees
    -0.77
     allowable
    -0.71
    cius
    -0.68
    pes
    -0.67
     Pwr
    -0.65
    culus
    -0.65
     gladly
    -0.63
     unnecessary
    -0.61
    rican
    -0.61
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.94
    tenance
    0.93
    ãĤ©
    0.91
    eers
    0.91
    naire
    0.89
    ation
    0.88
    uration
    0.88
    ãĥ´ãĤ¡
    0.87
    oufl
    0.85
    sylvania
    0.85
    Activations Density 0.056%

    No Known Activations