Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15037
    Prev
    Next
    INDEX
    Explanations

    references to the sun

    oai_token-act-pair · gpt-3.5-turbo

    the word "Sun" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    razil
    -0.85
    izabeth
    -0.83
    ngth
    -0.82
    ussen
    -0.78
     Hodg
    -0.75
    ailand
    -0.75
    ersive
    -0.74
    odied
    -0.71
    ÑĮ
    -0.70
     captcha
    -0.70
    POSITIVE LOGITS
    Sun
    1.04
     Sun
    0.94
    nah
    0.91
    sun
    0.90
    light
    0.86
    ray
    0.84
    shine
    0.83
    lit
    0.82
    Moon
    0.81
    beam
    0.80
    Activations Density 0.009%

    No Known Activations