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. 4-RES-JB
    6. 17829
    Prev
    Next
    INDEX
    Explanations

    verbs related to continuous actions or states

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "constantly."

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

    No Comments

    Negative Logits
    hemy
    -0.76
    tein
    -0.73
    rule
    -0.71
    IDA
    -0.70
    inals
    -0.69
    AMI
    -0.69
    istani
    -0.69
    OLOGY
    -0.66
    ENA
    -0.66
    nee
    -0.65
    POSITIVE LOGITS
     fluct
    0.90
     destro
    0.89
    motion
    0.88
     refreshed
    0.87
     spaced
    0.86
    ãĤ£
    0.85
     churn
    0.83
     replen
    0.82
     reinvent
    0.81
     evolving
    0.81
    Activations Density 0.013%

    No Known Activations