INDEX

Explanations

pronouns related to the subject "they."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

fastjson

-0.71

 MessageBoxIcon

-0.64

dime

-0.59

extAlignment

-0.58

zielle

-0.57

 onPage

-0.56

 itemprop

-0.55

ిన

-0.55

icrous

-0.54

 unknownFields

-0.54

POSITIVE LOGITS

 themselves

0.90

 they

0.80

They

0.80

Their

0.73

 THEY

0.73

all

0.73

THEY

0.72

themselves

0.71

 They

0.71

 berdua

0.71

Activations Density 0.176%

pronouns related to the subject "they."

No Comments

No Known Activations