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. 4428
    Prev
    Next
    INDEX
    Explanations

    phrases referencing substitution or replacement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substitution or replacements

    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
    enn
    -0.80
    doms
    -0.69
     Locked
    -0.69
    pol
    -0.68
    aan
    -0.68
    hest
    -0.68
    forums
    -0.68
    massive
    -0.64
    igators
    -0.64
    hing
    -0.64
    POSITIVE LOGITS
     substitute
    4.08
     substitutes
    3.30
     substituted
    2.34
     substitution
    2.25
     substit
    2.23
     Subst
    1.95
     replacement
    1.76
     replacements
    1.68
     replace
    1.54
     Replacement
    1.25
    Activations Density 0.012%

    No Known Activations