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. 12-RES-JB
    6. 15102
    Prev
    Next
    INDEX
    Explanations

    personal narratives and emotional expressions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of identity and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.51
     exploits
    -0.48
     prompts
    -0.45
     Hits
    -0.45
     highlights
    -0.44
     Stras
    -0.44
     Khe
    -0.43
     Cord
    -0.43
     aids
    -0.42
     Round
    -0.42
    POSITIVE LOGITS
    're
    0.99
    've
    0.95
    'm
    0.81
    'll
    0.80
     owe
    0.74
     haven
    0.74
     dont
    0.72
     don
    0.72
     intend
    0.71
     apologise
    0.70
    Activations Density 0.448%

    No Known Activations