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. 8-RES-JB
    6. 15625
    Prev
    Next
    INDEX
    Explanations

    words related to confinement or being isolated

    oai_token-act-pair · gpt-3.5-turbo

    narratives related to isolation and confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nieto
    -0.91
    FK
    -0.65
     Malays
    -0.64
     Rounds
    -0.64
    ãĥ¤
    -0.63
     rebate
    -0.63
    estamp
    -0.61
    iferation
    -0.61
     purchaser
    -0.61
     Spear
    -0.60
    POSITIVE LOGITS
     surrounded
    1.17
     solitude
    0.98
     limbo
    0.96
     rented
    0.94
     recl
    0.91
     obscurity
    0.91
     overlooking
    0.91
     confines
    0.90
     shack
    0.87
    livious
    0.85
    Activations Density 0.574%

    No Known Activations