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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12737
    Prev
    Next
    INDEX
    Explanations

    words related to meetings with Russian individuals and legal implications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meetings and legal issues involving Donald Trump and potential collusion with Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slayer
    -0.93
     CLR
    -0.84
     ILCS
    -0.84
     Cure
    -0.82
    galitarian
    -0.82
     econom
    -0.80
     herds
    -0.79
    byss
    -0.79
     Jagu
    -0.77
     Towns
    -0.77
    POSITIVE LOGITS
     Kislyak
    1.47
     Manafort
    1.41
     Kremlin
    1.35
    Russia
    1.33
     Podesta
    1.33
     Russia
    1.32
     Kushner
    1.31
     Flynn
    1.31
    Russian
    1.30
    afort
    1.29
    Activations Density 0.551%

    No Known Activations