© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or words related to geographical places

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific location, particularly "Rotterdam"

    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
    ELS
    -0.70
    uncture
    -0.66
    ¬¼
    -0.63
    ï¸
    -0.63
     disparate
    -0.61
     undermin
    -0.60
    UTERS
    -0.59
    olulu
    -0.58
    cean
    -0.58
    ा
    -0.58
    POSITIVE LOGITS
    geist
    1.33
    ranean
    1.10
    rors
    1.01
    rible
    0.99
    tainment
    0.97
    rane
    0.93
    flies
    0.90
    ribly
    0.89
    restrial
    0.86
    gom
    0.86
    Activations Density 0.036%

    No Known Activations