INDEX

Explanations

opening phrases or markers in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

StoryboardSegue

-1.10

 noDo

-1.02

SharedDtor

-0.93

ExtendWith

-0.93

SourceChecksum

-0.91

 ligiloj

-0.83

Aiheesta

-0.82

AndroidJUnit

-0.81

Geplaatst

-0.81

 BoxFit

-0.81

POSITIVE LOGITS

System

0.72

 System

0.61

Ph

0.52

Net

0.50

Math

0.49

ADM

0.49

异

0.49

お

0.49

gero

0.48

Anh

0.48

Activations Density 0.007%

opening phrases or markers in a text

No Comments

No Known Activations