© 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. 386
    Prev
    Next
    INDEX
    Explanations

    words that end with the suffix "ception"

    oai_token-act-pair · gpt-4-turbo

    words related to the concept of deception

    oai_token-act-pair · gpt-3.5-turbo

    words related to deception or perception

    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
     disg
    -0.84
     constituent
    -0.73
     reinstated
    -0.71
     comb
    -0.69
    accompan
    -0.66
    hed
    -0.65
     retreating
    -0.65
     shrinking
    -0.64
    far
    -0.64
     substituted
    -0.63
    POSITIVE LOGITS
    ception
    1.25
    ibility
    0.90
    ISION
    0.89
    onnaissance
    0.82
    imation
    0.81
    Fram
    0.81
    yip
    0.80
    UAL
    0.79
    agram
    0.79
    acies
    0.78
    Activations Density 0.017%

    No Known Activations