© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8459
    Prev
    Next
    INDEX
    Explanations

    locations or regions by cardinal directions

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and their relative positions within various regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sem
    -0.67
    sels
    -0.66
     coworkers
    -0.65
    rison
    -0.60
     whistleblowers
    -0.60
     voices
    -0.59
     executives
    -0.58
    CEO
    -0.58
     Cosponsors
    -0.57
     employees
    -0.57
    POSITIVE LOGITS
     northern
    1.02
     southwestern
    1.02
     southeastern
    0.98
     southwest
    0.98
     northeastern
    0.97
     southern
    0.94
    pop
    0.94
     neighbouring
    0.94
     northwestern
    0.93
     northwest
    0.93
    Activations Density 0.301%

    No Known Activations