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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 8038
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for something to be done or fulfilled

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "required" in various contexts related to obligations or necessities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.83
    ight
    -0.75
    sight
    -0.72
    stead
    -0.70
    ells
    -0.70
    cow
    -0.69
    ocent
    -0.69
    bench
    -0.68
    uay
    -0.66
    imir
    -0.65
    POSITIVE LOGITS
     disclosures
    0.86
     prerequisite
    0.80
     confir
    0.79
     guiActiveUn
    0.78
     unanim
    0.78
     introdu
    0.77
     obe
    0.77
     requirement
    0.76
     redund
    0.76
     compliance
    0.75
    Activations Density 0.017%

    No Known Activations