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. 2-RES-JB
    6. 3607
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "-ol" or "-ol9"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ol" and its variations, which likely represent references to specific names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Battles
    -0.77
    ãģ®éŃĶ
    -0.77
     ISS
    -0.71
     Citizen
    -0.68
     Anth
    -0.66
    æĸ¹
    -0.66
     Presidential
    -0.66
     UFO
    -0.65
     Healer
    -0.65
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.65
    POSITIVE LOGITS
    ateral
    1.17
    ipop
    1.14
    onial
    1.10
    ength
    1.07
    ounge
    1.01
    oad
    1.00
    oking
    0.98
    okia
    0.98
    ol
    0.98
    aptop
    0.96
    Activations Density 0.016%

    No Known Activations