© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14660
    Prev
    Next
    INDEX
    Explanations

    descriptions related to characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to qualitative descriptions of experiences and emotions

    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
    ornings
    -0.58
    ificantly
    -0.56
    Lago
    -0.53
    inion
    -0.53
    enture
    -0.52
    orthy
    -0.52
    Specific
    -0.52
     Shades
    -0.50
     Values
    -0.49
     unrelated
    -0.49
    POSITIVE LOGITS
    iest
    0.75
    liest
    0.71
    hest
    0.59
     fraternity
    0.58
    erest
    0.56
    osphere
    0.55
     portion
    0.55
     menace
    0.55
     fallacy
    0.53
     plag
    0.53
    Activations Density 1.171%

    No Known Activations