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. 10-RES-JB
    6. 14353
    Prev
    Next
    INDEX
    Explanations

    descriptions of family members

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships between mothers and their children

    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
    illary
    -0.71
    krit
    -0.67
    ript
    -0.65
    met
    -0.63
    Downloadha
    -0.62
    ickr
    -0.62
    esian
    -0.62
    ATIONS
    -0.61
    AE
    -0.60
    bilt
    -0.58
    POSITIVE LOGITS
     twins
    1.08
     slain
    0.88
     daughters
    0.84
     bride
    0.81
     murdered
    0.80
     Trayvon
    0.79
     three
    0.77
     deceased
    0.77
     Sandwich
    0.74
     autistic
    0.73
    Activations Density 0.043%

    No Known Activations