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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 8969
    Prev
    Next
    INDEX
    Explanations

    words related to personal relationships and communication

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]=
    -0.67
    bernatorial
    -0.63
    unction
    -0.59
    Wr
    -0.58
    PDATED
    -0.57
    served
    -0.57
     Heist
    -0.56
    adobe
    -0.56
     pestic
    -0.55
     summary
    -0.52
    POSITIVE LOGITS
     whom
    0.91
     strangers
    0.84
     counterparts
    0.83
     outside
    0.77
     coworkers
    0.74
     peers
    0.74
     beforehand
    0.73
     during
    0.71
     abroad
    0.71
     mates
    0.71
    Activations Density 0.496%

    No Known Activations