© 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. 6-RES-JB
    11. 439
    Prev
    Next
    INDEX
    Explanations

    references to creators or authors of various works

    oai_token-act-pair · gpt-3.5-turbo

    references to creators in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phia
    -0.72
    ishops
    -0.69
    olk
    -0.69
    olit
    -0.67
    UGE
    -0.66
     Stain
    -0.64
    eat
    -0.63
    abb
    -0.63
    ibaba
    -0.62
    eneg
    -0.61
    POSITIVE LOGITS
    creator
    0.86
     creator
    0.81
    ãĤº
    0.80
    paces
    0.80
     laureate
    0.76
    ãĤ´
    0.74
    ãĥķãĤ¡
    0.74
    emis
    0.72
    ãĥĨãĤ£
    0.71
    ãĥ´
    0.70
    Activations Density 0.021%

    No Known Activations