© 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. 9-RES-JB
    11. 17067
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirming information or confirming a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy theories and investigations

    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
    Interstitial
    -0.83
    intensive
    -0.75
    Incre
    -0.74
     Advice
    -0.73
     Obst
    -0.72
     barriers
    -0.72
     flexibility
    -0.70
    ļéĨĴ
    -0.70
     progressively
    -0.70
     ted
    -0.69
    POSITIVE LOGITS
     indeed
    1.24
     authentic
    0.94
     hoax
    0.91
     faked
    0.89
     existed
    0.88
     truth
    0.88
     exist
    0.88
    llah
    0.87
     authenticity
    0.86
    existent
    0.85
    Activations Density 0.649%

    No Known Activations