© 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. 2-RES-JB
    11. 17263
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations and proper nouns, particularly related to 'tropics' and 'Zeit'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of locations or terms related to geographical areas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.85
    IVER
    -0.75
    utive
    -0.70
     Beckham
    -0.70
     "$:/
    -0.70
    thood
    -0.69
    ι
    -0.69
    ÃįÃį
    -0.67
     Cyrus
    -0.65
     Buffer
    -0.64
    POSITIVE LOGITS
    geist
    0.84
    rophe
    0.83
    olog
    0.82
    ologies
    0.82
    ocrat
    0.81
    ocrats
    0.80
    ocalyptic
    0.79
    ological
    0.76
    ologically
    0.75
    ology
    0.75
    Activations Density 0.030%

    No Known Activations