© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2910
    Prev
    Next
    INDEX
    Explanations

    keywords related to CSS properties commonly used to manipulate background elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visual backgrounds and foregrounds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikh
    -0.83
    erion
    -0.79
    CVE
    -0.76
    hof
    -0.70
    eva
    -0.68
    nia
    -0.68
    oping
    -0.67
    bilt
    -0.66
    ribes
    -0.65
    thing
    -0.65
    POSITIVE LOGITS
     background
    1.07
     Background
    0.93
     backgrounds
    0.93
     backdrop
    0.87
     decoration
    0.79
     foreground
    0.77
    coat
    0.77
     color
    0.75
     colour
    0.73
    Color
    0.69
    Activations Density 0.011%

    No Known Activations