© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 3424
    Prev
    Next
    INDEX
    Explanations

    words related to political or ideological shifts, particularly the concept of defection

    oai_token-act-pair · gpt-3.5-turbo

    words related to deception or deceit

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.79
    viks
    -0.76
     Sioux
    -0.75
    trans
    -0.73
     Fargo
    -0.70
    sent
    -0.69
    frames
    -0.67
    mob
    -0.64
     QC
    -0.60
     lifetime
    -0.59
    POSITIVE LOGITS
    ection
    1.50
    ected
    1.32
    rador
    1.00
    ector
    0.98
    ect
    0.97
    ective
    0.96
    ipel
    0.88
    naire
    0.85
    ary
    0.84
    ocol
    0.83
    Activations Density 0.011%

    No Known Activations