© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11716
    Prev
    Next
    INDEX
    Explanations

    the phrase 'by no means'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote negation or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.65
     Pengu
    -0.64
    cair
    -0.63
    endas
    -0.62
     fug
    -0.60
    ibaba
    -0.59
    heed
    -0.58
    ilage
    -0.57
    anwhile
    -0.57
    roleum
    -0.57
    POSITIVE LOGITS
     means
    1.09
     standards
    1.04
     margins
    1.00
     Means
    0.99
     virtue
    0.86
     margin
    0.82
     reckoning
    0.81
    committee
    0.81
     measures
    0.78
    stand
    0.78
    Activations Density 0.104%

    No Known Activations