© 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. 14638
    Prev
    Next
    INDEX
    Explanations

    adjectives used to describe different aspects of a situation, such as fairness, controversy, danger, and innovation

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe intensity or severity 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
    adelphia
    -0.82
    ©¶æ
    -0.75
    aters
    -0.73
    culus
    -0.72
    tu
    -0.69
    lance
    -0.69
    Joy
    -0.68
    ipers
    -0.68
    iets
    -0.67
    urtles
    -0.67
    POSITIVE LOGITS
     alike
    1.11
     truths
    0.75
     striped
    0.74
     views
    0.73
     combinations
    0.73
     perspectives
    0.73
     opinions
    0.71
    ifiable
    0.71
     viewpoints
    0.70
     respectively
    0.70
    Activations Density 0.207%

    No Known Activations