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. 21167
    Prev
    Next
    INDEX
    Explanations

    words related to rights, obligations, responsibilities, and moral implications

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and obligations in various contexts

    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
    early
    -0.64
    hooting
    -0.62
    merce
    -0.60
    itsch
    -0.59
     Byr
    -0.59
    late
    -0.59
    PF
    -0.57
     diligent
    -0.57
    into
    -0.57
    steps
    -0.56
    POSITIVE LOGITS
     knack
    0.78
     vested
    0.76
    ointed
    0.66
    kees
    0.65
     lined
    0.63
    icum
    0.63
     say
    0.63
    Ö¼
    0.63
     credibility
    0.62
     redeem
    0.62
    Activations Density 0.247%

    No Known Activations