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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 720
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "William" in various contexts or forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Liam."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     locker
    -0.67
     phases
    -0.64
     periods
    -0.63
     chunks
    -0.63
     period
    -0.60
     scene
    -0.59
     phase
    -0.59
     charts
    -0.59
     stages
    -0.58
     depths
    -0.57
    POSITIVE LOGITS
    iam
    4.71
    liam
    1.44
    iaz
    1.23
    iw
    1.22
    iah
    1.20
    ias
    1.14
    iar
    1.13
    ia
    1.10
    IA
    1.09
    imus
    1.08
    Activations Density 0.009%

    No Known Activations