© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 10397
    Prev
    Next
    INDEX
    Explanations

    phrases related to perpetuating negative actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    political or social critique, particularly regarding support for certain agendas or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
    eline
    -0.73
     appreciated
    -0.70
    DragonMagazine
    -0.67
     survived
    -0.66
    tackle
    -0.66
    Clear
    -0.65
    imentary
    -0.65
    fax
    -0.65
     thanked
    -0.65
    POSITIVE LOGITS
     false
    1.16
     harmful
    1.16
     inaccurate
    1.15
     misinformation
    1.15
     falsehood
    1.13
     misleading
    1.12
     unrealistic
    1.11
     irresponsible
    1.11
     distorted
    1.09
     incorrect
    1.08
    Activations Density 1.703%

    No Known Activations