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. 9-RES-JB
    6. 8242
    Prev
    Next
    INDEX
    Explanations

    phrases related to forming bonds of trust and mutual understanding

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odder
    -0.70
     Canaver
    -0.66
    oway
    -0.65
     draconian
    -0.62
    ãĥ¯ãĥ³
    -0.61
    grim
    -0.61
     Forbes
    -0.60
     inflation
    -0.59
     NX
    -0.59
    yre
    -0.57
    POSITIVE LOGITS
     friendships
    1.18
     relationships
    1.15
     friendship
    1.08
     between
    1.07
     relationship
    1.05
    between
    1.00
     rapport
    0.98
     bonding
    0.97
     partners
    0.96
     partner
    0.96
    Activations Density 0.286%

    No Known Activations