© 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. 13664
    Prev
    Next
    INDEX
    Explanations

    the AT&T company name specifically formatted with '&' and 'T'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of AT&T 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
     prol
    -0.73
    lihood
    -0.71
     lucid
    -0.67
     vomiting
    -0.67
     Cth
    -0.66
     diam
    -0.64
    erva
    -0.64
     blur
    -0.63
    blance
    -0.62
     ejected
    -0.61
    POSITIVE LOGITS
    oday
    0.82
    MU
    0.79
    Store
    0.78
    TA
    0.78
    Cs
    0.77
    rex
    0.76
    ¹
    0.76
    amacare
    0.75
    REE
    0.75
    tin
    0.74
    Activations Density 0.009%

    No Known Activations