Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 24320
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or transition of control

    oai_token-act-pair · gpt-3.5-turbo

    references to legal complaints and formal accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experts
    -0.49
    jri
    -0.49
    lves
    -0.49
    illions
    -0.48
     endorsements
    -0.48
    ossibility
    -0.46
    Interstitial
    -0.44
    ÃĥÃĤ
    -0.44
     guesses
    -0.44
    educated
    -0.44
    POSITIVE LOGITS
     ABV
    0.65
     Drupal
    0.56
     Flavoring
    0.56
     Calais
    0.55
    SCP
    0.55
     MDMA
    0.54
     Transgender
    0.52
     Cannabis
    0.52
     Guant
    0.51
     SCP
    0.50
    Activations Density 1.661%

    No Known Activations