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. 12-RES-JB
    6. 15182
    Prev
    Next
    INDEX
    Explanations

    financial terms and performance metrics in a business context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    financial performance metrics related to movies and their box office success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brist
    -0.67
     framed
    -0.63
    enhagen
    -0.62
     Fein
    -0.61
    context
    -0.61
    Types
    -0.60
    lasses
    -0.60
     Concepts
    -0.59
    ribes
    -0.59
     Mons
    -0.58
    POSITIVE LOGITS
     haul
    1.28
     performance
    1.28
     success
    1.17
     result
    1.15
     record
    1.15
     accomplishment
    1.15
     attendance
    1.12
     turnout
    1.12
     victory
    1.11
     results
    1.10
    Activations Density 0.405%

    No Known Activations