© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1968
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of inner peace and self-awareness

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions related to feelings of freedom and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tax
    -0.75
    SpaceEngineers
    -0.74
    senal
    -0.74
    endment
    -0.71
    Federal
    -0.70
     Regulations
    -0.70
    hof
    -0.70
     Illegal
    -0.70
    illegal
    -0.67
    ospons
    -0.67
    POSITIVE LOGITS
     longing
    1.24
     emptiness
    1.18
     loneliness
    1.15
     melanch
    1.10
     sadness
    1.08
     melancholy
    1.07
     subconscious
    1.04
     consciousness
    1.02
     sorrow
    1.00
     empathy
    0.99
    Activations Density 1.306%

    No Known Activations