© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 13669
    Prev
    Next
    INDEX
    Explanations

    locations or places containing the word 'Sunny'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Sunny" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icult
    -0.86
    ngth
    -0.83
    igent
    -0.82
    erto
    -0.81
    ional
    -0.81
    urally
    -0.81
    ombat
    -0.80
    ulas
    -0.79
    phabet
    -0.78
    ovan
    -0.75
    POSITIVE LOGITS
     Leone
    1.03
     Sunny
    0.91
    vale
    0.79
     stroll
    0.77
    brook
    0.76
     Sunshine
    0.75
    creen
    0.74
     Brook
    0.71
     451
    0.70
     skies
    0.68
    Activations Density 0.063%

    No Known Activations