© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16053
    Prev
    Next
    INDEX
    Explanations

    text related to geographical or geological features such as monoliths and geological epochs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological formations and epochs, especially monoliths and the Pleistocene epoch

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ¦
    -0.78
    things
    -0.74
    Stats
    -0.73
    anth
    -0.71
    Connect
    -0.71
    lower
    -0.68
    Fel
    -0.66
    abus
    -0.66
    Statistics
    -0.66
    Pass
    -0.65
    POSITIVE LOGITS
    olithic
    1.19
    vironment
    0.94
    ocene
    0.90
    olith
    0.88
    hower
    0.83
    ocrine
    0.83
    osate
    0.80
    phrine
    0.78
    haar
    0.76
    ossus
    0.76
    Activations Density 0.031%

    No Known Activations