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. 10-RES-JB
    6. 19545
    Prev
    Next
    INDEX
    Explanations

    phrases related to aiding, abetting, and supporting various actions or causes

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases related to support and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Paper
    -0.89
     Clockwork
    -0.80
     Trash
    -0.76
    GMT
    -0.73
     Plasma
    -0.72
     Krypt
    -0.71
     Beam
    -0.70
     Skydragon
    -0.69
     Rivers
    -0.69
     Tooth
    -0.69
    POSITIVE LOGITS
     condone
    1.23
     encour
    1.22
     encourage
    1.22
     encouragement
    1.19
     assist
    1.17
     encouraged
    1.11
     endorse
    1.10
     encourages
    1.05
     assisting
    1.04
     facilitate
    1.04
    Activations Density 0.119%

    No Known Activations