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. 7-RES-JB
    6. 23291
    Prev
    Next
    INDEX
    Explanations

    phrases containing direct speech where someone is speaking to another person

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "said to"

    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
     fractures
    -0.68
    irez
    -0.62
    closed
    -0.61
     netted
    -0.60
    grounds
    -0.60
     deductions
    -0.58
     botched
    -0.57
     exemptions
    -0.57
     contested
    -0.56
    soDeliveryDate
    -0.56
    POSITIVE LOGITS
    wered
    1.05
     me
    0.94
    speak
    0.85
    ilet
    0.81
     us
    0.80
    asts
    0.79
     him
    0.77
    pless
    0.77
    ggles
    0.77
     imitate
    0.76
    Activations Density 0.082%

    No Known Activations