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. 3603
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction and damage to property, as well as human and political rights violations

    oai_token-act-pair · gpt-3.5-turbo

    references to property rights and violations

    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
    igmat
    -0.75
    oward
    -0.73
    eus
    -0.72
    agonists
    -0.69
     Unsure
    -0.68
    Dispatch
    -0.68
     Outbreak
    -0.67
     Chaser
    -0.65
    umbn
    -0.65
     onset
    -0.65
    POSITIVE LOGITS
     livelihood
    1.47
     belongings
    1.37
     priceless
    1.35
     property
    1.25
     assets
    1.25
     precious
    1.19
     freedoms
    1.18
     lives
    1.18
    property
    1.17
     liberties
    1.14
    Activations Density 0.683%

    No Known Activations