© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11587
    Prev
    Next
    INDEX
    Explanations

    instances where something is taken to the next level or to an extreme

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an escalation or intensification of situations or concepts

    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
    lla
    -0.64
    etta
    -0.63
    istani
    -0.60
    time
    -0.59
     discriminated
    -0.59
    rice
    -0.58
    ior
    -0.58
    icipated
    -0.58
    ulty
    -0.57
     waiting
    -0.56
    POSITIVE LOGITS
     stride
    0.99
     extremes
    0.74
     heart
    0.74
    soType
    0.70
    unal
    0.70
    */(
    0.67
    borgh
    0.67
     Seriously
    0.65
     granted
    0.62
    igious
    0.61
    Activations Density 0.066%

    No Known Activations