© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3150
    Prev
    Next
    INDEX
    Explanations

    mentions of strong bonds and connections between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to friendship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acco
    -0.74
    printed
    -0.68
    cise
    -0.67
    FT
    -0.66
     Printed
    -0.66
    detail
    -0.66
    nit
    -0.64
    gun
    -0.64
    apor
    -0.63
    consumer
    -0.62
    POSITIVE LOGITS
     between
    1.03
    yip
    0.84
     friendship
    0.84
     friendships
    0.80
     relationship
    0.80
    between
    0.80
     ties
    0.79
     reconnect
    0.78
     banter
    0.77
     relationships
    0.76
    Activations Density 0.096%

    No Known Activations