© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20440
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of intervention or obstruction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interfere" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    sal
    -0.84
    tu
    -0.75
    Bio
    -0.73
    True
    -0.73
    Template
    -0.70
    Sam
    -0.69
    ndra
    -0.69
    mber
    -0.68
    chal
    -0.67
    tim
    -0.67
    POSITIVE LOGITS
     interfere
    1.24
     interfered
    1.14
     interfering
    1.10
     interference
    0.89
     medd
    0.87
     adversely
    0.83
    awei
    0.82
     newsp
    0.79
     undermin
    0.79
     overl
    0.77
    Activations Density 0.007%

    No Known Activations