© 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. 10-RES-JB
    11. 2673
    Prev
    Next
    INDEX
    Explanations

    words related to personal growth and positive achievements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal growth and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.87
     dummy
    -0.84
    proxy
    -0.68
    cens
    -0.68
    lat
    -0.68
    SQL
    -0.67
    rimp
    -0.67
    nick
    -0.65
    blocking
    -0.65
     Cosponsors
    -0.65
    POSITIVE LOGITS
     enlightenment
    1.68
     happiness
    1.59
     immortality
    1.44
     harmony
    1.43
     spirituality
    1.42
     salvation
    1.39
     liberation
    1.34
     excellence
    1.34
     righteousness
    1.34
     prosperity
    1.34
    Activations Density 0.421%

    No Known Activations