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. 3601
    Prev
    Next
    INDEX
    Explanations

    commands or calls to take specific actions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or demands for social and political change

    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
    emed
    -0.72
    facing
    -0.66
    amen
    -0.65
    bered
    -0.64
    oother
    -0.63
    liest
    -0.63
     restored
    -0.62
    Ready
    -0.62
    aired
    -0.62
    myra
    -0.61
    POSITIVE LOGITS
     wasteful
    1.17
     cynicism
    1.06
     prejudice
    1.04
     harmful
    1.02
     unnecessary
    1.02
     prejudices
    1.01
     distortions
    1.01
     hypocrisy
    1.00
     misconceptions
    1.00
     injustice
    1.00
    Activations Density 0.398%

    No Known Activations