© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20290
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations

    oai_token-act-pair · gpt-3.5-turbo

    references to groups, particularly in a military or organized context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereditary
    -0.69
     Remastered
    -0.68
    luaj
    -0.65
     inheritance
    -0.64
     Promise
    -0.64
     patents
    -0.63
     Chronic
    -0.63
     Fundamental
    -0.62
     bankruptcy
    -0.62
    isSpecialOrderable
    -0.62
    POSITIVE LOGITS
     disembark
    1.18
     parked
    1.15
     stroll
    1.02
     perched
    1.02
     wandering
    1.00
     seated
    0.99
     wandered
    0.98
     walking
    0.98
     boarded
    0.96
     stranded
    0.95
    Activations Density 1.253%

    No Known Activations