INDEX

Explanations

structured data and code syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

principalColumn

-0.97

writeFieldEnd

-0.97

 nakalista

-0.91

 itſelf

-0.86

Geplaatst

-0.83

 onPostExecute

-0.82

 незавершена

-0.82

 HasFactory

-0.82

 JpaRepository

-0.82

IsMutable

-0.82

POSITIVE LOGITS

...

0.51

<h1>

0.51

らかに

0.49

adin

0.49

0.48

↵

0.45

 gospod

0.45

memberOf

0.44

0.43

Климат

0.43

Activations Density 0.724%

structured data and code syntax

No Comments

No Known Activations