INDEX

Explanations

discussions related to risk, security, and crisis management in contexts involving technology and health

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zecz

-0.64

 ModelExpression

-0.61

Hentet

-0.59

uxxxx

-0.59

BagConstraints

-0.56

帖最后由

-0.55

<()>

-0.54

 jScrollPane

-0.52

 EdgeInsets

-0.52

GMENT

-0.52

POSITIVE LOGITS

 Brexit

0.92

 Trump

0.90

 coronavirus

0.85

 ISIS

0.82

 Coronavirus

0.80

 COVID

0.80

Brexit

0.78

 Rohing

0.74

 opioid

0.73

 Covid

0.73

Activations Density 0.403%

discussions related to risk, security, and crisis management in contexts involving technology and health

No Comments

No Known Activations