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. 15003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of being in need

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a need for assistance or support

    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
    link
    -0.77
     istg
    -0.71
    hesis
    -0.68
    ula
    -0.63
    imilar
    -0.63
    opus
    -0.62
    nels
    -0.62
    mask
    -0.60
    must
    -0.59
    ucle
    -0.59
    POSITIVE LOGITS
     course
    0.79
    umbn
    0.75
     sorts
    0.74
    ãĤ¦
    0.72
     luck
    0.72
     fate
    0.71
     justice
    0.67
     honour
    0.67
    ãģĤ
    0.66
    ãģĦ
    0.65
    Activations Density 0.106%

    No Known Activations