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. 6-RES-JB
    6. 21650
    Prev
    Next
    INDEX
    Explanations

    complex compound words or phrases that include a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical descriptors, especially related to physical traits or shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.80
    URA
    -0.75
    çīĪ
    -0.73
     KH
    -0.71
    aea
    -0.70
     Macy
    -0.67
     guiActiveUn
    -0.64
     holiest
    -0.64
    EStream
    -0.64
    liest
    -0.63
    POSITIVE LOGITS
    angled
    0.78
    fit
    0.77
    angles
    0.74
    arrow
    0.73
    angle
    0.72
    nered
    0.70
    iability
    0.68
    pole
    0.67
    tailed
    0.65
    tun
    0.64
    Activations Density 0.185%

    No Known Activations