© 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. 11-RES-JB
    11. 10093
    Prev
    Next
    INDEX
    Explanations

    keywords related to political scandals and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to political scandals and allegations involving collusion and foreign influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dak
    -0.59
     Bahá
    -0.59
     rebirth
    -0.57
    Redd
    -0.57
     defin
    -0.56
    urally
    -0.55
     Chaser
    -0.54
     rugged
    -0.53
    ctl
    -0.53
     DSM
    -0.53
    POSITIVE LOGITS
     during
    0.88
     pertaining
    0.86
     BEFORE
    0.85
    during
    0.83
    foundation
    0.82
     associates
    0.81
     laundering
    0.80
     inappropriately
    0.80
     dossier
    0.79
     before
    0.79
    Activations Density 0.308%

    No Known Activations