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. 11-RES-JB
    6. 10471
    Prev
    Next
    INDEX
    Explanations

    similar or identical words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of usage and similarity in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ropolis
    -0.70
    ursions
    -0.64
    ablishment
    -0.64
    lav
    -0.64
     impending
    -0.64
    riots
    -0.64
    irable
    -0.63
     needing
    -0.62
    ansion
    -0.62
    progress
    -0.62
    POSITIVE LOGITS
     technique
    1.27
     terminology
    1.27
     pseudonym
    1.26
     techniques
    1.22
     tactic
    1.17
     pronouns
    1.09
     analogy
    1.07
     tactics
    1.07
     euphem
    1.04
     method
    1.04
    Activations Density 0.355%

    No Known Activations