INDEX

Explanations

the word "you" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 صوتيه

-0.70

 للاسماء

-0.69

 propOrder

-0.64

GenerationType

-0.62

 LUMP

-0.61

 onCancelled

-0.60

stretchr

-0.58

 оригіналу

-0.58

 also

-0.57

 Egipto

-0.57

POSITIVE LOGITS

antwoorde

0.58

 Meksiku

0.55

 Specifically

0.53

道

0.51

 Waray

0.51

picuous

0.51

ñado

0.50

 preoccup

0.48

exels

0.48

sterious

0.48

Activations Density 0.181%

the word "you" in various contexts

No Comments

No Known Activations