© 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. 7-RES-JB
    11. 23056
    Prev
    Next
    INDEX
    Explanations

    references to the word "Land"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Land Rover."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.79
    utic
    -0.76
    hift
    -0.74
     sidx
    -0.74
    vernment
    -0.72
     dism
    -0.67
    æĢ
    -0.66
     Qiao
    -0.65
    pta
    -0.64
    ught
    -0.64
    POSITIVE LOGITS
    scape
    1.24
    marks
    1.12
    lord
    1.10
    mark
    1.08
    lords
    1.05
    grave
    1.02
    owner
    0.99
    locked
    0.98
    fill
    0.93
    mass
    0.90
    Activations Density 0.023%

    No Known Activations