© 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. 7915
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disagreement or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to political accountability and ethical considerations

    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
    SPONSORED
    -0.70
    ema
    -0.69
    HCR
    -0.67
     Returning
    -0.65
    icum
    -0.63
    Exit
    -0.63
    mes
    -0.61
    911
    -0.61
    combat
    -0.61
    hide
    -0.61
    POSITIVE LOGITS
     pretty
    0.87
     kinda
    0.82
     plenty
    0.80
     kidding
    0.79
     spoilers
    0.75
     typo
    0.70
     nerds
    0.69
     crappy
    0.69
     ;)
    0.68
     ner
    0.68
    Activations Density 0.607%

    No Known Activations