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. 20389
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching through or sifting through data or physical objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to searching or sifting through information

    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
    ajor
    -0.61
    FLAG
    -0.60
    Production
    -0.59
    MAT
    -0.57
    Sit
    -0.56
     dependence
    -0.56
    Sov
    -0.56
     leverage
    -0.55
    roit
    -0.55
    Shift
    -0.55
    POSITIVE LOGITS
     archives
    0.98
     menus
    0.90
     databases
    0.89
     Archives
    0.84
     folders
    0.81
     shelves
    0.76
     browsing
    0.76
     directories
    0.76
     bins
    0.75
    herer
    0.75
    Activations Density 0.198%

    No Known Activations