INDEX

Explanations

words associated with status or significant events

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

Code, API calls, or technical language

np_acts-logits-general · gemini-2.0-flash

app development and technical actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 للمعارف

-0.93

 flesta

-0.91

issauga

-0.90

konomi

-0.86

sø

-0.81

fører

-0.79

 שוליים

-0.79

tableFuture

-0.79

 senare

-0.77

POSITIVE LOGITS

ting

0.78

gggg

0.73

GGGG

0.68

inguishing

0.66

Goi

0.64

AppSettings

0.64

PendingIntent

0.63

 enro

0.63

HIN

0.62

tdb

0.62

Activations Density 0.385%

words associated with status or significant events

Code, API calls, or technical language

app development and technical actions

No Comments

No Known Activations