© 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. 17741
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or events, such as "Spadina" and "Fort York"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and specific geographic or urban terms

    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
     guiActiveUn
    -0.72
    ĸļ
    -0.72
    ovych
    -0.71
    nih
    -0.67
     Mour
    -0.66
     "$:/
    -0.65
     wiser
    -0.65
    £ı
    -0.63
    hyde
    -0.61
    hower
    -0.61
    POSITIVE LOGITS
    hett
    0.85
    aker
    0.75
    essim
    0.74
    lator
    0.73
     Zar
    0.70
    oslav
    0.70
    atin
    0.69
    idon
    0.68
    ooter
    0.66
    olini
    0.66
    Activations Density 0.053%

    No Known Activations