Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 7626
    Prev
    Next
    INDEX
    Explanations

    technical and descriptive words related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    references to trends and innovations in technology and gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retali
    -0.69
    displayText
    -0.67
     concess
    -0.66
    uana
    -0.65
    ewitness
    -0.65
     Minister
    -0.64
     Volunteers
    -0.64
     calmly
    -0.62
    orget
    -0.61
     Charity
    -0.61
    POSITIVE LOGITS
     genre
    0.88
     fanbase
    0.84
     indie
    0.83
     sci
    0.82
    luster
    0.80
     geek
    0.80
     nerd
    0.78
     nerds
    0.77
     Transformers
    0.77
     MMO
    0.77
    Activations Density 0.836%

    No Known Activations