INDEX

Explanations

terms related to healthiness and dietary patterns

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

preceding "eating", "diet", or "nutrition"

np_acts-logits-general · gemini-2.0-flash

healthy, secure, valid, or identifiable states

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Abp

-0.80

yntaxException

-0.80

MessageOf

-0.77

 يتيمه

-0.74

 виправивши

-0.70

aarrggbb

-0.70

 cipolla

-0.69

 CreateTagHelper

-0.66

sizeCache

-0.65

 متعلقه

-0.65

POSITIVE LOGITS

ness

0.91

neſs

0.88

NESS

0.81

enough

0.68

nesses

0.68

 ness

0.64

 ſeveral

0.62

 enough

0.62

nefs

0.60

oke

0.59

Activations Density 0.733%

terms related to healthiness and dietary patterns

preceding "eating", "diet", or "nutrition"

healthy, secure, valid, or identifiable states

No Comments

No Known Activations