© 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. 11-RES-JB
    11. 18737
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or emotional states or actions

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive and negative traits or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.65
    éļ
    -0.64
    audi
    -0.61
     bene
    -0.61
     Luxem
    -0.59
     entirety
    -0.59
     ascertain
    -0.58
     wil
    -0.58
    other
    -0.56
     Neurolog
    -0.55
    POSITIVE LOGITS
     quicker
    0.93
     ASAP
    0.85
     quickly
    0.85
     again
    0.84
     traction
    0.82
     faster
    0.77
     sooner
    0.77
    */(
    0.75
    quick
    0.74
     puberty
    0.73
    Activations Density 0.193%

    No Known Activations