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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14703
    Prev
    Next
    INDEX
    Explanations

    terms related to being contained or restricted

    oai_token-act-pair · gpt-3.5-turbo

    the concept of confinement or restriction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foundation
    -0.64
    soDeliveryDate
    -0.62
    estamp
    -0.62
    CF
    -0.60
    alky
    -0.60
     ethic
    -0.59
    Eth
    -0.59
     Ily
    -0.56
     HRC
    -0.56
    df
    -0.56
    POSITIVE LOGITS
     confinement
    1.05
     confined
    0.90
    untarily
    0.82
    ĸļ
    0.79
     confines
    0.77
    icut
    0.76
     pigeon
    0.72
     nudity
    0.72
     quarantine
    0.71
     shack
    0.70
    Activations Density 0.012%

    No Known Activations