© 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. 13636
    Prev
    Next
    INDEX
    Explanations

    mentions or terms related to piracy or pirated content

    oai_token-act-pair · gpt-3.5-turbo

    references to piracy and corporate entities

    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
     guiActiveUnfocused
    -0.70
    BOX
    -0.66
    LOG
    -0.65
    bows
    -0.64
    BOOK
    -0.63
     Tactics
    -0.60
    ONES
    -0.60
     Masquerade
    -0.60
     Ops
    -0.59
    MENTS
    -0.59
    POSITIVE LOGITS
    acy
    1.20
    atism
    1.06
    ongyang
    1.04
    acies
    0.91
    eworks
    0.90
    rito
    0.90
    acist
    0.89
    abulary
    0.88
    amic
    0.85
    atio
    0.85
    Activations Density 0.047%

    No Known Activations