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. 11292
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures and materials

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of objects or phenomena with specific spatial or structural characteristics

    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
    enegger
    -0.74
     corrid
    -0.67
    ÃĥÃĤ
    -0.65
    PDATE
    -0.63
     Vaugh
    -0.63
    AUD
    -0.62
    oppable
    -0.61
    acebook
    -0.61
    vertisement
    -0.59
    ONSORED
    -0.59
    POSITIVE LOGITS
     tray
    0.67
    Rot
    0.67
     texture
    0.67
     brush
    0.65
     diameter
    0.61
     coat
    0.61
     fins
    0.61
     metallic
    0.60
     edges
    0.59
     surfaces
    0.58
    Activations Density 0.944%

    No Known Activations