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. 3132
    Prev
    Next
    INDEX
    Explanations

    mentions of personal possession or body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to personal ownership or possessive terms concerning health and well-being

    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
    ilts
    -0.81
    apo
    -0.79
     Uriel
    -0.77
    trak
    -0.73
    vous
    -0.73
    wik
    -0.71
     Originally
    -0.70
     Goes
    -0.66
    raq
    -0.66
    witch
    -0.66
    POSITIVE LOGITS
     own
    1.55
     favourite
    1.11
     favorite
    1.09
     surroundings
    1.02
     opponent
    1.00
     adversary
    0.97
    ocard
    0.97
     spouse
    0.93
     fingertips
    0.92
     imagination
    0.92
    Activations Density 0.115%

    No Known Activations