Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22722
    Prev
    Next
    INDEX
    Explanations

    words related to happiness or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with happiness and achievement

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

    No Comments

    Negative Logits
     inadequ
    -0.69
     Wasteland
    -0.63
     claws
    -0.62
     air
    -0.60
     artillery
    -0.60
     Grimes
    -0.60
     explosives
    -0.59
     Genocide
    -0.59
     juveniles
    -0.58
     discipl
    -0.58
    POSITIVE LOGITS
    ful
    1.60
    fully
    1.57
    isters
    1.09
    fulness
    1.06
    full
    1.04
    icles
    1.02
    icular
    0.96
    eful
    0.94
    imil
    0.93
    urious
    0.93
    Activations Density 0.808%

    No Known Activations