INDEX

Explanations

references to legal actions and procedural terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 greateſt

-0.77

 betweenstory

-0.77

 beſt

-0.74

 myſelf

-0.69

 Autorisations

-0.68

 pleaſure

-0.67

 NSCoder

-0.62

 laſt

-0.62

MarshalTo

-0.61

 diſt

-0.61

POSITIVE LOGITS

 חיצוניים

0.99

 kasarigan

0.82

 שוליים

0.81

 autorytatywna

0.79

protoimpl

0.72

üyada

0.72

 jScrollPane

0.67

सन्दर्भ

0.66

ValueStyle

0.65

withId

0.61

Activations Density 1.392%

references to legal actions and procedural terminology

No Comments

No Known Activations