© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    the word "don't" followed by a negative verb contraction

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases expressing dissent

    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
     Reloaded
    -0.76
    Reviewer
    -0.76
    soType
    -0.74
    çĦ
    -0.72
    estern
    -0.71
     Penguin
    -0.69
    itiz
    -0.69
    pter
    -0.66
     behavi
    -0.64
    foundland
    -0.64
    POSITIVE LOGITS
     necessarily
    1.08
     bother
    1.00
     anymore
    0.91
    ude
    0.84
    cha
    0.81
     hesitate
    0.81
     seem
    0.81
     expect
    0.81
     know
    0.80
    rave
    0.80
    Activations Density 0.100%

    No Known Activations