© 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. 0-RES-JB
    11. 11301
    Prev
    Next
    INDEX
    Explanations

    references to the word "Sunshine" with a high activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Sunshine" in various contexts

    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
    rodu
    -0.71
    ideo
    -0.69
    grave
    -0.68
    hist
    -0.68
    gra
    -0.68
    aleb
    -0.67
    eport
    -0.66
    burg
    -0.65
     targ
    -0.65
    gru
    -0.65
    POSITIVE LOGITS
     Sunshine
    4.25
     sunshine
    1.89
    shine
    1.59
     Sunrise
    1.20
     Darling
    1.18
    noon
    1.14
     Peach
    1.02
     Shine
    1.00
     Mayo
    1.00
    flower
    0.91
    Activations Density 0.038%

    No Known Activations