© 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. 6-RES-JB
    11. 1552
    Prev
    Next
    INDEX
    Explanations

    locations or directions, specifically related to cardinal or ordinal directions such as North, South, East, and West

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations or directional indicators

    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
    apego
    -0.86
    20439
    -0.76
    quished
    -0.75
    ramid
    -0.72
    porary
    -0.70
    umbnails
    -0.68
    hler
    -0.67
    vous
    -0.67
    Website
    -0.65
    xual
    -0.65
    POSITIVE LOGITS
     Heights
    1.00
     Bay
    0.89
     Africa
    0.85
    borough
    0.85
     Springs
    0.82
    town
    0.81
     Janeiro
    0.80
     Valley
    0.80
     Angeles
    0.80
     suburb
    0.79
    Activations Density 0.181%

    No Known Activations