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. 7-RES-JB
    6. 10108
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and state control

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government, state control, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.79
    IAS
    -0.71
     Sour
    -0.70
    Austral
    -0.69
     Alto
    -0.68
     Bree
    -0.65
    oche
    -0.64
     Marathon
    -0.64
    OUT
    -0.64
    DEN
    -0.63
    POSITIVE LOGITS
     decre
    0.97
     regulation
    0.92
     morality
    0.90
     machinery
    0.90
     powerless
    0.90
     tyranny
    0.89
     apparatus
    0.88
     monopoly
    0.88
     coerc
    0.86
     bureaucracy
    0.86
    Activations Density 0.499%

    No Known Activations