INDEX

Explanations

situations involving the word "in" within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 définiti

-0.53

ívne

-0.53

 Reap

-0.51

updateOne

-0.46

ittaa

-0.45

OutputType

-0.45

由

-0.43

vė

-0.43

观的

-0.43

getUid

-0.43

POSITIVE LOGITS

 فريبيس

1.16

 חיצוניים

0.74

basicConfig

0.71

Przypisy

0.68

ordion

0.68

]]

0.66

!*\

0.64

Билгалдахарш

0.64

)__

0.63

Rujuakan

0.63

Activations Density 0.315%

situations involving the word "in" within various contexts

No Comments

No Known Activations