© 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. 9-RES-JB
    11. 1418
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    varying expressions of being and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 9 - joy

    No Comments

    Negative Logits
    ongyang
    -0.72
     strain
    -0.70
    ulence
    -0.67
     rigs
    -0.67
    idation
    -0.66
    anova
    -0.66
    plings
    -0.66
     inference
    -0.66
     Reason
    -0.64
     comprehension
    -0.64
    POSITIVE LOGITS
     able
    1.25
     reunited
    0.96
     reminded
    0.96
     alive
    0.87
     treated
    0.86
     photographed
    0.85
     seated
    0.84
     involved
    0.84
     surrounded
    0.83
    held
    0.83
    Activations Density 0.120%

    No Known Activations