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. 16934
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" and its variations in context

    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
    pite
    -0.78
    amins
    -0.75
    irez
    -0.68
    owa
    -0.68
    hesda
    -0.65
    headers
    -0.65
    redits
    -0.63
    works
    -0.63
     incurred
    -0.63
    quartered
    -0.63
    POSITIVE LOGITS
     him
    0.89
     us
    0.77
     them
    0.70
     inquire
    0.69
     reporters
    0.69
     me
    0.65
    psy
    0.64
     someone
    0.63
     talk
    0.63
     strangers
    0.63
    Activations Density 0.051%

    No Known Activations