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. 7357
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking actions against someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take down."

    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
    inen
    -0.78
    athi
    -0.74
    0000000000000000
    -0.69
    ĸļ
    -0.69
    uno
    -0.67
    Streamer
    -0.66
    yne
    -0.65
    ira
    -0.63
    ¶ħ
    -0.63
    ��
    -0.63
    POSITIVE LOGITS
     stairs
    1.02
    grading
    0.77
    stairs
    0.74
     weeds
    0.73
    graded
    0.72
     stakes
    0.72
     clipboard
    0.71
     notices
    0.71
    river
    0.68
     hill
    0.67
    Activations Density 0.023%

    No Known Activations