© 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. 6-RES-JB
    11. 14612
    Prev
    Next
    INDEX
    Explanations

    words related to opposite sides or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicting parties or perspectives in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cles
    -0.69
     Countdown
    -0.63
     Miko
    -0.60
    agna
    -0.59
     dehyd
    -0.59
    RON
    -0.58
     Berry
    -0.58
     Polaris
    -0.58
     Assist
    -0.58
    nce
    -0.57
    POSITIVE LOGITS
    side
    0.86
     alike
    0.83
     sides
    0.81
     thereof
    0.74
    pace
    0.72
    cale
    0.72
     combatants
    0.70
     concede
    0.69
     equally
    0.69
     hust
    0.69
    Activations Density 0.018%

    No Known Activations