INDEX

Explanations

references to dining experiences and restaurant reviews

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

Signals negative sentiment or disappointment

np_acts-logits-general · gemini-2.0-flash

negative evaluations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 naturalmente

-0.68

enderror

-0.65

LayoutConstraint

-0.62

وفة

-0.62

onedDateTime

-0.61

FunctionFlags

-0.61

 lyder

-0.61

omány

-0.61

homonymie

-0.60

 idéale

-0.60

POSITIVE LOGITS

 unprofessional

0.99

Terrible

0.97

 horrible

0.97

Awful

0.96

Horrible

0.96

 Terrible

0.95

 terrible

0.94

 appalling

0.94

 poor

0.93

Worse

0.92

Activations Density 0.107%

references to dining experiences and restaurant reviews

Signals negative sentiment or disappointment

negative evaluations

No Comments

No Known Activations