© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    geographic measurements and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spatial dimensions and measurements

    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
    alogue
    -0.84
    uni
    -0.81
    ãĥīãĥ©
    -0.78
    istine
    -0.76
    immers
    -0.74
    inatory
    -0.74
    porary
    -0.72
    Trend
    -0.70
    inse
    -0.67
    raltar
    -0.66
    POSITIVE LOGITS
     radius
    1.24
     Radius
    0.97
     circumference
    0.90
    radius
    0.86
     diameter
    0.83
     Thick
    0.75
     separation
    0.74
     curv
    0.73
     cavity
    0.73
     distance
    0.72
    Activations Density 0.010%

    No Known Activations