© 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. 9361
    Prev
    Next
    INDEX
    Explanations

    words related to spatial locations, specifically focusing on the upper part of a physical space

    oai_token-act-pair · gpt-3.5-turbo

    references to the upper class in various contexts

    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
     Machina
    -0.79
    eln
    -0.77
    uality
    -0.77
    tnc
    -0.76
    ensable
    -0.76
    rx
    -0.73
    roma
    -0.71
    atile
    -0.71
    undo
    -0.71
    inatory
    -0.69
    POSITIVE LOGITS
    most
    1.26
     lobe
    0.89
     earners
    0.80
     thigh
    0.79
     shaft
    0.78
     jaw
    0.78
     lip
    0.78
     bounds
    0.78
     limb
    0.78
     tier
    0.77
    Activations Density 0.025%

    No Known Activations