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. 13811
    Prev
    Next
    INDEX
    Explanations

    names of political figures or people involved in scandals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Abbas and Abram

    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
    nces
    -0.91
    omore
    -0.86
    ndra
    -0.68
     Doom
    -0.67
    IGH
    -0.66
     Savior
    -0.65
    bones
    -0.65
     OMG
    -0.64
     Flavoring
    -0.62
    gow
    -0.62
    POSITIVE LOGITS
    raham
    1.01
    ilities
    0.85
    ortion
    0.83
    ãĥĩ
    0.80
    aic
    0.79
    osta
    0.78
    bey
    0.77
    pour
    0.77
    rod
    0.77
    bed
    0.76
    Activations Density 0.015%

    No Known Activations