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. 6-RES-JB
    6. 13115
    Prev
    Next
    INDEX
    Explanations

    phrases related to attracting people or things

    oai_token-act-pair · gpt-3.5-turbo

    the word "attract" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oops
    -0.66
     procedure
    -0.64
    hal
    -0.62
     surviving
    -0.60
     forearm
    -0.58
     vault
    -0.57
    jab
    -0.57
    itcher
    -0.57
    miah
    -0.56
    chens
    -0.56
    POSITIVE LOGITS
     attention
    0.82
    GGGGGGGG
    0.80
     attract
    0.78
    weights
    0.77
    entious
    0.76
    kefeller
    0.75
     attracts
    0.74
     attracted
    0.74
    tails
    0.72
    dinand
    0.71
    Activations Density 0.036%

    No Known Activations