© 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. 16874
    Prev
    Next
    INDEX
    Explanations

    mentions of shortcomings or deficiencies

    oai_token-act-pair · gpt-3.5-turbo

    references to deficiencies or lacks in various contexts

    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
    nee
    -0.76
    aunder
    -0.74
    eday
    -0.73
    eeper
    -0.71
    YN
    -0.67
    ipple
    -0.64
    initely
    -0.63
    oulos
    -0.63
    ucc
    -0.63
    visor
    -0.62
    POSITIVE LOGITS
     anymore
    0.96
     adequately
    0.85
     altogether
    0.85
     nor
    0.84
     whatsoever
    0.79
     expectations
    0.78
    smanship
    0.76
     adequate
    0.76
     manpower
    0.75
    yet
    0.73
    Activations Density 0.242%

    No Known Activations