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. 13407
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to sorcery or magic

    oai_token-act-pair · gpt-3.5-turbo

    references to sorcery or magical elements in various contexts

    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
    ichick
    -0.78
    ITNESS
    -0.78
     Reloaded
    -0.76
     Gutenberg
    -0.72
     Cherokee
    -0.68
     Palmer
    -0.67
     UID
    -0.65
     Papua
    -0.65
    urally
    -0.61
    Bang
    -0.58
    POSITIVE LOGITS
    cery
    1.31
    ority
    1.27
    cer
    1.06
    cha
    0.99
    kel
    0.95
    bent
    0.91
    oshenko
    0.91
    nery
    0.88
    hett
    0.88
    adin
    0.87
    Activations Density 0.018%

    No Known Activations