Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4448
    Prev
    Next
    INDEX
    Explanations

    verbs related to ability or expertise

    oai_token-act-pair · gpt-3.5-turbo

    indicative verbs and phrases that describe the state of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heny
    -0.88
     Franch
    -0.76
     Awakens
    -0.72
    ulla
    -0.71
    orks
    -0.71
    backer
    -0.68
     oneself
    -0.67
     ourselves
    -0.67
    uld
    -0.65
     waits
    -0.65
    POSITIVE LOGITS
     impecc
    0.94
     priceless
    0.93
     hampered
    0.93
     waning
    0.87
     questionable
    0.86
     mirrored
    0.86
     hindered
    0.84
     admirable
    0.84
     bolstered
    0.84
     undeniable
    0.83
    Activations Density 0.304%

    No Known Activations