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. 11-RES-JB
    6. 8139
    Prev
    Next
    INDEX
    Explanations

    prompts or encouragements to try something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage trying or giving something a chance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     matters
    -0.88
    APD
    -0.74
    urable
    -0.69
     agreements
    -0.69
    quartered
    -0.68
     tensions
    -0.67
    lihood
    -0.67
     barriers
    -0.65
     grievances
    -0.65
    Orig
    -0.64
    POSITIVE LOGITS
     try
    1.12
     shot
    1.03
     wh
    0.78
     spin
    0.77
     thumbs
    0.77
    Try
    0.77
     toss
    0.76
     listen
    0.76
     go
    0.75
    SourceFile
    0.75
    Activations Density 0.055%

    No Known Activations