© 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. 2389
    Prev
    Next
    INDEX
    Explanations

    phrases related to sources of emotional or creative stimulation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of inspiration and encouragement

    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
    Not in Any Lists

    No Comments

    Negative Logits
    estation
    -0.81
    iop
    -0.76
    alon
    -0.70
    ntil
    -0.70
    ophon
    -0.69
    minster
    -0.68
     Canad
    -0.68
    eln
    -0.68
    olit
    -0.67
    iable
    -0.64
    POSITIVE LOGITS
    iration
    1.12
     inspiration
    1.08
     Cosponsors
    0.96
     muse
    0.91
     inspiring
    0.88
     inspir
    0.75
     artwork
    0.75
     Insp
    0.74
     inspire
    0.71
     spark
    0.70
    Activations Density 0.068%

    No Known Activations