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. 9-RES-JB
    6. 15785
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Dennis"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Dennis or Rodney

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eting
    -0.87
    ige
    -0.83
    ees
    -0.81
    istically
    -0.81
    isations
    -0.80
    igr
    -0.80
    arial
    -0.80
    falls
    -0.80
    ouched
    -0.78
    bow
    -0.75
    POSITIVE LOGITS
    é¾
    0.79
     Fuk
    0.76
    kefeller
    0.74
    CAST
    0.65
    lectic
    0.64
    ç«
    0.64
    £ı
    0.62
    åŃ
    0.62
     franch
    0.62
    çīĪ
    0.62
    Activations Density 0.205%

    No Known Activations