© 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. 0-RES-JB
    11. 629
    Prev
    Next
    INDEX
    Explanations

    terms related to security and government agencies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security agencies and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inspir
    -0.72
    lier
    -0.72
     panc
    -0.67
    letes
    -0.66
     incarn
    -0.65
     figur
    -0.65
    aver
    -0.65
    ettes
    -0.64
     compositions
    -0.64
    Beg
    -0.64
    POSITIVE LOGITS
     Security
    3.84
    Security
    2.85
    security
    2.61
     security
    2.53
     cybersecurity
    1.50
     Safety
    1.44
     Privacy
    1.37
     Secure
    1.34
     Intelligence
    1.29
     Surveillance
    1.26
    Activations Density 0.014%

    No Known Activations