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. 16973
    Prev
    Next
    INDEX
    Explanations

    phrases that describe something as a basic or fundamental concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey basic explanations or definitions

    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
     wisely
    -0.86
     promptly
    -0.77
     appropriately
    -0.77
     urgently
    -0.75
     preferably
    -0.74
     moreover
    -0.73
     vividly
    -0.72
     surely
    -0.68
     inevitably
    -0.68
    acious
    -0.68
    POSITIVE LOGITS
    maxwell
    0.79
    NetMessage
    0.72
     rewriting
    0.71
    veyard
    0.70
    SpaceEngineers
    0.69
    osher
    0.68
     guiActiveUn
    0.67
    earable
    0.67
    uga
    0.66
    pmwiki
    0.65
    Activations Density 0.155%

    No Known Activations