© 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. 7-RES-JB
    11. 17025
    Prev
    Next
    INDEX
    Explanations

    words related to happiness or positive outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happy" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 7 - joy

    No Comments

    Negative Logits
     impulse
    -0.73
     Nile
    -0.68
    ħĭ
    -0.67
    ctica
    -0.65
    trl
    -0.64
     Scotia
    -0.64
     guiActiveUn
    -0.64
    heses
    -0.63
     IMAGES
    -0.60
    oute
    -0.60
    POSITIVE LOGITS
    ened
    1.27
    ening
    1.23
    iness
    1.11
    iest
    1.08
    ily
    1.07
    ier
    1.00
    eners
    0.92
    icial
    0.90
    ert
    0.88
    eret
    0.87
    Activations Density 0.025%

    No Known Activations