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. 1-RES-JB
    6. 19479
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "raid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HRC
    -0.76
    å¦
    -0.72
     Understand
    -0.67
     Elev
    -0.65
     Extrem
    -0.65
    Victoria
    -0.64
     Holden
    -0.64
     ARC
    -0.64
     Geo
    -0.64
    Albert
    -0.63
    POSITIVE LOGITS
     raid
    1.43
     raids
    1.33
     raiding
    1.25
     raided
    1.07
    ishly
    0.94
    Raid
    0.88
    raid
    0.87
    iversary
    0.82
     plunder
    0.82
    arded
    0.78
    Activations Density 0.008%

    No Known Activations