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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12835
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly focusing on individuals named "Janet"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Janet or Betsy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.99
    Sov
    -0.78
    doors
    -0.74
    FTWARE
    -0.72
    gran
    -0.67
    amaz
    -0.67
    juven
    -0.64
    76561
    -0.64
    taboola
    -0.64
    fare
    -0.64
    POSITIVE LOGITS
     Mock
    1.00
     Janet
    0.96
    ovic
    0.79
     Nicol
    0.78
     Reno
    0.76
    ellen
    0.73
    clips
    0.72
     Jackson
    0.72
    ovan
    0.71
     Walton
    0.71
    Activations Density 0.009%

    No Known Activations