INDEX

Explanations

references to the pronoun "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

stdc

-0.75

 PLWABN

-0.52

tonode

-0.51

 Akismet

-0.51

 sisters

-0.50

 <<<<<<<<<<<<<<

-0.50

 frères

-0.49

LookAnd

-0.49

 hermanas

-0.49

Descarga

-0.49

POSITIVE LOGITS

You

0.73

fjspx

0.71

 سكانية

0.70

You

0.69

protoimpl

0.67

Види

0.65

YOU

0.65

 kiệm

0.64

AlterField

0.64

 Савезне

0.62

Activations Density 0.152%

references to the pronoun "you."

No Comments

No Known Activations