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. 3-RES-JB
    6. 14311
    Prev
    Next
    INDEX
    Explanations

    mentions of emissions or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to emissions and their impacts on the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Else
    -0.93
    ivas
    -0.81
    inosaur
    -0.75
    ISH
    -0.74
    anova
    -0.73
    rooms
    -0.72
    slice
    -0.71
    ciating
    -0.68
     Else
    -0.68
    amina
    -0.68
    POSITIVE LOGITS
     emissions
    1.35
     emission
    1.14
     emitting
    1.04
     emit
    0.95
     dioxide
    0.93
     pollution
    0.93
     gases
    0.92
     emitted
    0.90
     emits
    0.87
     pollutants
    0.84
    Activations Density 0.026%

    No Known Activations