© 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. 2-RES-JB
    11. 8421
    Prev
    Next
    INDEX
    Explanations

    phrases related to infringement or violation

    oai_token-act-pair · gpt-3.5-turbo

    instances of patent infringement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.81
    agan
    -0.68
    brace
    -0.64
    tu
    -0.63
    roth
    -0.62
    hall
    -0.60
    adi
    -0.60
    =-=-=-=-=-=-=-=-
    -0.60
    oses
    -0.60
    bern
    -0.60
    POSITIVE LOGITS
     infring
    1.30
     infringement
    1.23
     infringing
    1.05
    yrights
    0.80
    emonium
    0.78
     proble
    0.70
    terness
    0.70
     counterfe
    0.69
     inhibition
    0.69
    rodu
    0.68
    Activations Density 0.007%

    No Known Activations