© 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. 7778
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Cadbury'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cad"

    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
    ãģį
    -0.69
     Borders
    -0.69
    à
    -0.66
     pity
    -0.64
     TABLE
    -0.63
    icago
    -0.62
    SOURCE
    -0.61
     sorry
    -0.61
     Fargo
    -0.60
    square
    -0.60
    POSITIVE LOGITS
    enza
    0.94
    eter
    0.92
    elong
    0.92
    enary
    0.91
     Cad
    0.91
    rown
    0.91
    illac
    0.91
    zos
    0.86
    arette
    0.86
    epend
    0.86
    Activations Density 0.027%

    No Known Activations