© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "mind-boggling."

    oai_token-act-pair · gpt-3.5-turbo

    references to "ogg" indicating a focus on audio or sound-related content

    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
    ction
    -0.71
     diligence
    -0.64
     Janeiro
    -0.63
     Antiqu
    -0.63
    ¶ħ
    -0.62
    idency
    -0.61
    terday
    -0.60
    âĸ¬
    -0.59
    wives
    -0.59
    PRES
    -0.58
    POSITIVE LOGITS
    oths
    0.98
    ogg
    0.96
    s
    0.92
    iants
    0.92
    oola
    0.92
    shire
    0.90
    ause
    0.89
    urations
    0.87
    ernaut
    0.86
    regate
    0.86
    Activations Density 0.020%

    No Known Activations