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. 18869
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights

    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
    aco
    -0.67
    -+-+
    -0.63
     Sark
    -0.62
    intage
    -0.62
    ALSE
    -0.62
    VERSION
    -0.60
     steam
    -0.60
    âĸ¬
    -0.59
     threaded
    -0.59
     Clover
    -0.59
    POSITIVE LOGITS
     rights
    1.14
     Rights
    1.07
    rights
    1.06
     conferred
    0.83
     freedoms
    0.83
    ileged
    0.83
     protections
    0.79
     afforded
    0.77
     entitle
    0.77
    hell
    0.76
    Activations Density 0.024%

    No Known Activations