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. 5-RES-JB
    6. 15005
    Prev
    Next
    INDEX
    Explanations

    phrases related to being emotionally or physically affected by something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struck" used in various contexts, indicating impact or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iliary
    -0.74
    enser
    -0.74
    ilon
    -0.72
    umption
    -0.72
    ORY
    -0.71
    omore
    -0.67
    adian
    -0.67
    ensor
    -0.65
    resy
    -0.64
    ŀ
    -0.64
    POSITIVE LOGITS
     striking
    0.83
     resemb
    0.79
     struck
    0.78
    tered
    0.75
     strike
    0.75
    ters
    0.74
    achi
    0.71
     mast
    0.69
     Strikes
    0.66
    breakers
    0.66
    Activations Density 0.017%

    No Known Activations