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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 9364
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    traits related to descriptions of objects and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idas
    -0.72
    nia
    -0.71
    tnc
    -0.69
    arth
    -0.67
     Lutheran
    -0.67
    nian
    -0.67
    achus
    -0.66
    otti
    -0.65
    ebook
    -0.63
    brew
    -0.63
    POSITIVE LOGITS
     adherents
    0.79
     ensu
    0.78
     tentacles
    0.74
    tones
    0.66
     twists
    0.65
     twist
    0.65
     gimmick
    0.65
     Its
    0.63
    Its
    0.62
     hull
    0.60
    Activations Density 0.854%

    No Known Activations