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. 8-RES-JB
    6. 8701
    Prev
    Next
    INDEX
    Explanations

    commonly used terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms that indicate common usage or frequency in various contexts

    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
     Integrity
    -0.72
    acity
    -0.67
    orate
    -0.67
    anth
    -0.65
    letico
    -0.64
     deadlines
    -0.62
    jit
    -0.62
     kickoff
    -0.62
     Shape
    -0.62
    legraph
    -0.62
    POSITIVE LOGITS
     referred
    1.24
     seen
    1.10
     regarded
    1.09
    entimes
    1.03
     mistaken
    1.01
     known
    1.01
     termed
    1.00
     associated
    1.00
     viewed
    0.99
     abbrevi
    0.99
    Activations Density 0.060%

    No Known Activations