INDEX

Explanations

references to professional attire and clothing choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

telser

-0.58

TagHelpers

-0.56

 gynhyrchwyd

-0.55

 CreateTagHelper

-0.54

 الحره

-0.53

 grieve

-0.51

VOICE

-0.50

 jScrollPane

-0.49

InputBorder

-0.48

ledge

-0.46

POSITIVE LOGITS

 wearer

0.70

 wearing

0.68

 wore

0.66

wearing

0.61

 препратки

0.61

 wears

0.60

 Wearing

0.60

 kleding

0.59

 dresses

0.59

 fashions

0.58

Activations Density 0.217%

references to professional attire and clothing choices

No Comments

No Known Activations