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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 10558
    Prev
    Next
    INDEX
    Explanations

    strings that resemble hexadecimal color codes

    oai_token-act-pair · gpt-3.5-turbo

    specific references to music-related elements or terminology

    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
    etheless
    -0.67
     hem
    -0.65
     modest
    -0.62
    jriwal
    -0.60
     nursing
    -0.59
     customary
    -0.59
     recalling
    -0.58
     mourning
    -0.58
     foul
    -0.56
    assetsadobe
    -0.55
    POSITIVE LOGITS
    idae
    1.05
    aceae
    0.87
    Sys
    0.87
    Ops
    0.83
    Tube
    0.82
    atron
    0.81
    Corp
    0.77
    Fit
    0.77
    Zero
    0.76
    Club
    0.76
    Activations Density 0.324%

    No Known Activations