© 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. 0-RES-JB
    11. 9695
    Prev
    Next
    INDEX
    Explanations

    phrases or statements that require verification

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cole
    -0.71
     Darling
    -0.67
     Karl
    -0.65
     Cole
    -0.65
    going
    -0.63
    riks
    -0.62
     pand
    -0.62
    enta
    -0.61
     Tend
    -0.60
    olt
    -0.60
    POSITIVE LOGITS
     verify
    3.42
     verification
    2.63
     verifying
    2.59
     verified
    2.51
     Verify
    2.13
     validate
    1.73
    verified
    1.73
     confirm
    1.60
     VER
    1.43
     corrobor
    1.42
    Activations Density 0.018%

    No Known Activations