Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 23299
    Prev
    Next
    INDEX
    Explanations

    information related to military presence or operation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to security and military presence

    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
    nikov
    -0.78
     actu
    -0.74
     congratulations
    -0.73
    VIDIA
    -0.72
     inventor
    -0.70
    alys
    -0.68
    HTML
    -0.67
     congr
    -0.67
     surgeons
    -0.65
     expert
    -0.65
    POSITIVE LOGITS
     vicinity
    1.16
     downtown
    1.14
     nearby
    1.13
     streets
    1.10
     Downtown
    1.07
     town
    1.05
     northern
    1.00
     southwestern
    1.00
     eastern
    0.97
     northeastern
    0.97
    Activations Density 0.812%

    No Known Activations