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. 10514
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense and actions that someone or something can do

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating demands or requests made by entities

    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
     chronological
    -0.66
     Vet
    -0.63
     KGB
    -0.63
    onet
    -0.61
    Subject
    -0.60
     Diesel
    -0.59
    omew
    -0.58
     Boss
    -0.57
     Lawn
    -0.57
     differentiation
    -0.57
    POSITIVE LOGITS
     deem
    0.78
    imeters
    0.70
    abouts
    0.70
     sorely
    0.69
    des
    0.68
    llers
    0.68
    atel
    0.68
     emulate
    0.67
    assy
    0.65
     deems
    0.65
    Activations Density 0.285%

    No Known Activations