© 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. 2-RES-JB
    11. 9353
    Prev
    Next
    INDEX
    Explanations

    words related to mental health, particularly terms associated with various mental health conditions like lunacy or delirium

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "lunatic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¢âĢ¢
    -0.80
    ORN
    -0.77
    åĬ
    -0.75
    Constructed
    -0.74
    eff
    -0.72
     Norn
    -0.71
    LECT
    -0.70
     Continued
    -0.69
    EVA
    -0.69
    USE
    -0.67
    POSITIVE LOGITS
    acies
    1.21
     lun
    1.20
    acy
    1.08
    cheon
    1.05
    atic
    0.97
    atics
    0.95
    atical
    0.94
    gement
    0.88
    acists
    0.82
    udicrous
    0.82
    Activations Density 0.005%

    No Known Activations