© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22200
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the need to understand, learn, or view information

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

    No Comments

    Negative Logits
     Sox
    -0.74
     benches
    -0.72
    luster
    -0.69
    ãĤ´ãĥ³
    -0.67
     pie
    -0.65
     lawy
    -0.64
    ItemTracker
    -0.64
    pie
    -0.63
     towels
    -0.60
     seams
    -0.59
    POSITIVE LOGITS
    ealous
    0.74
    ISE
    0.74
    hent
    0.73
     RELEASE
    0.71
     nutshell
    0.70
    uate
    0.69
     Kyl
    0.69
    ANCE
    0.63
    ovych
    0.62
     Lem
    0.60
    Activations Density 0.164%

    No Known Activations