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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 13613
    Prev
    Next
    INDEX
    Explanations

    statements related to rights and freedoms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individual rights and freedoms

    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
    soDeliveryDate
    -0.78
    likely
    -0.72
    Missing
    -0.67
    torn
    -0.67
    fortunately
    -0.67
    pur
    -0.66
    Avg
    -0.65
    aeus
    -0.65
    ampa
    -0.64
    yrinth
    -0.64
    POSITIVE LOGITS
     freely
    0.90
    enance
    0.85
     anonymously
    0.78
     openly
    0.77
     lawfully
    0.77
     unlimited
    0.72
     immoral
    0.70
     liberties
    0.70
     arbitrary
    0.69
    thood
    0.68
    Activations Density 0.356%

    No Known Activations