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. 18046
    Prev
    Next
    INDEX
    Explanations

    connectors or conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    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
    mpeg
    -0.90
    ige
    -0.86
    actionDate
    -0.81
    activity
    -0.80
    AU
    -0.77
    SPA
    -0.75
    quad
    -0.70
    panel
    -0.69
    vec
    -0.69
    ema
    -0.69
    POSITIVE LOGITS
    romeda
    0.93
     secondly
    0.79
    rew
    0.77
    rogen
    0.76
     optionally
    0.74
     furthermore
    0.73
     Kushner
    0.69
     maybe
    0.68
     vo
    0.68
     vice
    0.68
    Activations Density 0.080%

    No Known Activations