INDEX

Explanations

references to the front of objects or concepts

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

ukone

-0.86

MeasureSpec

-0.80

 escolar

-0.76

 poussière

-0.75

styrelsen

-0.75

ulink

-0.73

verständ

-0.73

 culturelles

-0.72

 naturelle

-0.71

TintMode

-0.71

POSITIVE LOGITS

 front

1.40

 FRONT

1.38

 Front

1.35

front

1.32

Front

1.28

FRONT

1.19

 Fron

1.06

Fron

1.06

 fron

1.04

 fronts

1.03

Activations Density 0.047%

references to the front of objects or concepts

No Comments

No Known Activations