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. 16627
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal oppression and marginalization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to marginalized and disenfranchised populations

    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
    sis
    -0.87
    odium
    -0.80
    orah
    -0.80
    etric
    -0.76
    othy
    -0.75
    aline
    -0.72
    tein
    -0.70
    etrical
    -0.68
    ibal
    -0.66
    ope
    -0.66
    POSITIVE LOGITS
     marginalized
    0.80
     minorities
    0.75
     Voices
    0.75
    Marginal
    0.74
     bystanders
    0.70
     populations
    0.70
     communities
    0.69
    marg
    0.69
    ĨĴ
    0.68
     disadvantaged
    0.66
    Activations Density 0.046%

    No Known Activations