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. 0-RES-JB
    6. 20768
    Prev
    Next
    INDEX
    Explanations

    keywords denoting a difference or unique characteristic

    oai_token-act-pair · gpt-3.5-turbo

    the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enough
    -0.71
     control
    -0.65
     recovery
    -0.63
     savings
    -0.63
     management
    -0.63
     close
    -0.62
     values
    -0.60
     cap
    -0.60
     access
    -0.59
     arm
    -0.59
    POSITIVE LOGITS
    also
    3.13
    sometimes
    1.82
    often
    1.67
    formerly
    1.53
    actually
    1.48
    along
    1.46
    both
    1.43
    usually
    1.42
    again
    1.37
    literally
    1.33
    Activations Density 0.016%

    No Known Activations