Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8374
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental impact or consciousness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental, social, and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klu
    -0.72
    ials
    -0.68
     Flavoring
    -0.67
    lag
    -0.66
    cess
    -0.64
     mechanisms
    -0.64
    ger
    -0.63
     pains
    -0.61
     Isle
    -0.61
     Gifts
    -0.60
    POSITIVE LOGITS
     tuned
    0.89
    ically
    0.82
     regenerate
    0.81
    UNCH
    0.80
     mature
    0.79
     calibrated
    0.77
     detonated
    0.77
    bane
    0.76
    guided
    0.76
     satisfying
    0.76
    Activations Density 0.024%

    No Known Activations