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. 19784
    Prev
    Next
    INDEX
    Explanations

    terms related to oil and energy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oil or petroleum

    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
    bub
    -0.73
    leness
    -0.66
     besie
    -0.65
    river
    -0.63
    cedes
    -0.63
    aurus
    -0.62
    rification
    -0.60
    lie
    -0.60
    rien
    -0.60
     Blanc
    -0.59
    POSITIVE LOGITS
    ers
    1.18
    owship
    1.15
    ties
    0.99
    ership
    0.97
    erers
    0.88
    ential
    0.83
    erer
    0.83
    ength
    0.81
    ously
    0.79
    aughs
    0.79
    Activations Density 0.035%

    No Known Activations