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. 16563
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a different perspective or viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "Some," indicating a focus on generalizations or ambiguous statements

    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
    SPONSORED
    -0.74
     borne
    -0.67
    gon
    -0.61
    tainment
    -0.60
    uyomi
    -0.60
    isition
    -0.59
    ively
    -0.59
    ettes
    -0.59
    hips
    -0.58
    edin
    -0.57
    POSITIVE LOGITS
    body
    1.14
    how
    1.12
    place
    1.04
    ones
    0.86
    etheless
    0.81
     mornings
    0.77
    HOW
    0.74
     semblance
    0.74
    quartered
    0.70
    ONE
    0.70
    Activations Density 0.102%

    No Known Activations