© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    promotional advertisements and possibly legal terms

    oai_token-act-pair · gpt-3.5-turbo

    advertisement-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
     plus
    -0.70
     hoard
    -0.61
     unaccount
    -0.60
     Stellar
    -0.58
     fireball
    -0.58
     thrown
    -0.57
    +.
    -0.57
     neut
    -0.57
     photographed
    -0.57
     camp
    -0.57
    POSITIVE LOGITS
    20439
    0.99
    Loading
    0.92
    Prev
    0.85
    Related
    0.84
    Advertisements
    0.82
    esian
    0.80
    ||||
    0.80
    Privacy
    0.79
    Comments
    0.79
    PLA
    0.78
    Activations Density 0.114%

    No Known Activations