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. 9-RES-JB
    6. 10816
    Prev
    Next
    INDEX
    Explanations

    numerical values mentioned in relation to money, statistics, or quantities

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liament
    -0.75
     wisely
    -0.73
    eworld
    -0.68
     srfAttach
    -0.67
    stakes
    -0.66
    atown
    -0.65
    soDeliveryDate
    -0.64
     nurture
    -0.63
    æĦ
    -0.61
     backdrop
    -0.60
    POSITIVE LOGITS
     deaths
    1.21
     fatalities
    1.12
     suicides
    1.02
     complaints
    0.97
     fewer
    0.96
     layoffs
    0.94
     homicides
    0.93
     losses
    0.91
     arrests
    0.90
     casualties
    0.88
    Activations Density 0.295%

    No Known Activations