© 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. 10-RES-JB
    11. 2925
    Prev
    Next
    INDEX
    Explanations

    words related to negative actions or misunderstandings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mistakes or misunderstandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cake
    -0.64
    frey
    -0.60
    CHAT
    -0.59
    stones
    -0.57
    ModLoader
    -0.55
     uphill
    -0.55
    instein
    -0.55
     stakes
    -0.55
     hubs
    -0.54
    chat
    -0.54
    POSITIVE LOGITS
    vous
    1.05
    ceived
    0.90
    ceptions
    0.89
    akable
    0.78
    ventures
    0.78
    omers
    0.76
    gotten
    0.75
    rued
    0.73
    inations
    0.73
    gments
    0.71
    Activations Density 0.045%

    No Known Activations