INDEX

Explanations

words related to instructions or guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

IsContent

-0.71

ArgsConstructor

-0.64

StoryboardSegue

-0.57

}{@

-0.55

Điều

-0.52

windowFixed

-0.51

featureID

-0.48

InputBorder

-0.48

OptionsMenu

-0.48

Nhưng

-0.48

POSITIVE LOGITS

ième

0.52

🏾

0.51

ness

0.51

glMatrixMode

0.51

 TextInputType

0.50

nya

0.49

empêcher

0.47

 medesimo

0.47

dshaw

0.47

🏿

0.47

Activations Density 0.010%

words related to instructions or guidance

No Comments

No Known Activations