© 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. 8-RES-JB
    11. 12383
    Prev
    Next
    INDEX
    Explanations

    phrases related to dropping or letting something fall

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dropping" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLA
    -0.72
    âĸ¬
    -0.72
    SELECT
    -0.69
    "]=>
    -0.69
    WM
    -0.68
    ove
    -0.68
    APH
    -0.65
    WR
    -0.64
    orth
    -0.63
    MAL
    -0.63
    POSITIVE LOGITS
     bombshell
    1.15
     bombs
    0.95
     leaflets
    0.93
     hints
    0.89
     inhib
    0.78
     towel
    0.74
     balloons
    0.72
     hammer
    0.70
     Bombs
    0.70
     Tow
    0.69
    Activations Density 0.089%

    No Known Activations