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. 7-RES-JB
    6. 14908
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making an effort to achieve something

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs, particularly "to" followed by an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prem
    -0.68
     Uses
    -0.67
     Klu
    -0.65
    furt
    -0.65
     Eucl
    -0.64
     Participation
    -0.64
     Highest
    -0.63
     Fires
    -0.62
     WARNING
    -0.62
     Fired
    -0.62
    POSITIVE LOGITS
     emulate
    1.19
     promote
    1.12
     improve
    1.08
     commemorate
    1.08
     conserve
    1.06
     alleviate
    1.05
     prepare
    1.04
     deserve
    1.02
     accommodate
    1.02
    pless
    1.01
    Activations Density 0.080%

    No Known Activations