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. 0-RES-JB
    6. 2982
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and software, specifically focusing on the mention of "RGB" and "Photoshop"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital imaging software and color models

    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
    tel
    -0.81
     Dickinson
    -0.81
    heed
    -0.71
     du
    -0.68
     Dai
    -0.67
     pav
    -0.66
     Fitzgerald
    -0.66
     haw
    -0.65
     Eck
    -0.65
     fal
    -0.65
    POSITIVE LOGITS
     RGB
    3.43
    RGB
    2.42
     Photoshop
    2.12
     rgb
    1.33
     gamma
    1.06
    oshop
    1.02
     HDR
    1.01
    Gam
    1.00
    gb
    0.96
     RG
    0.95
    Activations Density 0.026%

    No Known Activations