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. 6-RES-JB
    6. 18023
    Prev
    Next
    INDEX
    Explanations

    misspelled words and errors in writing

    oai_token-act-pair · gpt-3.5-turbo

    instances of spelling errors and corrections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.82
    Progress
    -0.81
    galitarian
    -0.80
     resil
    -0.79
     contrace
    -0.76
    egu
    -0.75
    urus
    -0.74
    tnc
    -0.73
    MRI
    -0.72
    stasy
    -0.72
    POSITIVE LOGITS
     spelling
    1.23
     pronoun
    1.19
     phrases
    1.06
     spelled
    1.05
     phrase
    1.04
     pronouns
    1.01
     typo
    1.00
     words
    0.99
     verb
    0.99
     initials
    0.98
    Activations Density 0.257%

    No Known Activations