© 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. 1-RES-JB
    11. 20159
    Prev
    Next
    INDEX
    Explanations

    mentions of mental states or conditions, especially focusing on the term 'mentally'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Companies
    -0.64
     Rue
    -0.63
     Emmanuel
    -0.63
     Mek
    -0.61
    Ak
    -0.61
     Cullen
    -0.61
     Gal
    -0.61
     Quartz
    -0.61
     Bou
    -0.60
     Foley
    -0.60
    POSITIVE LOGITS
     defic
    1.07
     mentally
    0.93
     retarded
    0.88
    ependent
    0.84
    etically
    0.82
    pecially
    0.81
    endon
    0.80
    zona
    0.80
     conclud
    0.77
    itialized
    0.76
    Activations Density 0.005%

    No Known Activations