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. 10-RES-JB
    6. 15565
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to people's actions and feelings towards others

    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
     Cla
    -0.71
     Dunk
    -0.64
     Burst
    -0.61
     Beast
    -0.61
     Bott
    -0.60
     Vent
    -0.60
     Marine
    -0.58
     Radiation
    -0.58
     Explosion
    -0.58
     Sloan
    -0.57
    POSITIVE LOGITS
     deem
    1.16
     deems
    1.15
     dislike
    1.15
     hadn
    1.14
     shouldn
    1.10
     couldn
    1.05
     disliked
    1.04
     disapprove
    1.01
     cannot
    0.99
     otherwise
    0.99
    Activations Density 0.148%

    No Known Activations