© 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. 8-RES-JB
    11. 17850
    Prev
    Next
    INDEX
    Explanations

    action-related terms and consequences like criticisms, failures, and surprises

    oai_token-act-pair · gpt-3.5-turbo

    topics related to economic and social criticisms or failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.69
     Vaugh
    -0.64
     Kardash
    -0.55
     Afgh
    -0.55
     innocence
    -0.54
     Axis
    -0.53
     marqu
    -0.52
     Hust
    -0.51
     Benn
    -0.51
     Tile
    -0.51
    POSITIVE LOGITS
    obyl
    0.69
    etheless
    0.68
    tics
    0.65
    urtles
    0.65
    \":
    0.63
    CVE
    0.60
    abin
    0.60
    Ĥª
    0.59
    ikers
    0.58
    cigarettes
    0.58
    Activations Density 0.541%

    No Known Activations