© 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 EvalsExportsinterp-engineNEWAPI 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. 9152
    Prev
    Next
    INDEX
    Explanations

    reading numerical values with decimals

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly statistics and measurements

    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
     SCP
    -0.65
     Jiu
    -0.65
     CAM
    -0.64
     SET
    -0.64
     SL
    -0.63
     Monarch
    -0.63
     ISS
    -0.61
     camping
    -0.60
     eSports
    -0.60
     bast
    -0.60
    POSITIVE LOGITS
    28
    1.06
    35
    1.05
    26
    1.04
    25
    1.04
    29
    1.04
    23
    1.03
    38
    1.02
    36
    1.02
    45
    1.01
    30
    1.00
    Activations Density 0.131%

    No Known Activations