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. 3-RES-JB
    6. 10394
    Prev
    Next
    INDEX
    Explanations

    references to characters or concepts related to martial arts and warfare

    oai_token-act-pair · gpt-3.5-turbo

    references to soldiers and characters associated with military themes

    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
    itching
    -0.84
    eking
    -0.81
     reserve
    -0.72
    oulos
    -0.72
    andre
    -0.70
    oard
    -0.70
    oing
    -0.68
    ighting
    -0.66
     mint
    -0.66
    itions
    -0.65
    POSITIVE LOGITS
     Soldier
    0.93
     Spy
    0.82
    vana
    0.82
     Mode
    0.79
     Nation
    0.77
    Jet
    0.77
    Agent
    0.76
     Generations
    0.73
    Girl
    0.72
     Tracker
    0.72
    Activations Density 0.032%

    No Known Activations