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. 10-RES-JB
    6. 13447
    Prev
    Next
    INDEX
    Explanations

    references to organizations and initiatives related to specific causes or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to human rights and advocacy organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accelerator
    -0.83
     bluff
    -0.82
     muster
    -0.82
     lessons
    -0.81
     simulator
    -0.77
     advis
    -0.77
     doom
    -0.77
     lesson
    -0.76
     sober
    -0.76
     melt
    -0.76
    POSITIVE LOGITS
     Subst
    1.18
     Diseases
    1.18
     Devices
    1.16
     Terrorism
    1.16
     Practices
    1.15
     Activities
    1.15
     Crimes
    1.09
     Discrimination
    1.07
     Abuse
    1.05
     Occupations
    1.03
    Activations Density 0.119%

    No Known Activations