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. 9-RES-JB
    6. 15181
    Prev
    Next
    INDEX
    Explanations

    phrases related to external factors or circumstances impacting a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to circumstances and external factors affecting situations

    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
    tein
    -0.82
    inis
    -0.78
    onyms
    -0.77
    ocry
    -0.77
    tained
    -0.76
    sterdam
    -0.74
    cott
    -0.73
    ership
    -0.72
    phabet
    -0.71
    athon
    -0.70
    POSITIVE LOGITS
     factors
    1.32
     circumstances
    1.05
     intervened
    1.05
     pressures
    1.04
     unforeseen
    1.03
     variables
    1.03
     influencing
    1.01
     Factors
    1.01
     dictates
    0.99
     influences
    0.99
    Activations Density 0.316%

    No Known Activations