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. 7-RES-JB
    6. 16632
    Prev
    Next
    INDEX
    Explanations

    words related to technology and technical processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology, specifically those involving electronics and media

    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
    Ô
    -0.81
    abwe
    -0.80
     Tradable
    -0.70
    awatts
    -0.67
    nos
    -0.67
    Õ
    -0.65
    haps
    -0.65
    Mont
    -0.64
    steen
    -0.63
    ONES
    -0.63
    POSITIVE LOGITS
     portion
    1.09
     apparatus
    0.96
     mechanism
    0.95
     system
    0.92
     machine
    0.91
     layer
    0.91
     axis
    0.90
     module
    0.87
     element
    0.87
     container
    0.87
    Activations Density 0.428%

    No Known Activations