INDEX

Explanations

concepts related to personal relationships and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 họ

-0.72

彼らは

-0.72

they

-0.71

 mereka

-0.66

mereka

-0.64

They

-0.63

 Họ

-0.62

彼らの

-0.62

Ils

-0.61

помним

-0.60

POSITIVE LOGITS

my

2.18

me

1.94

 myself

1.59

 mijn

1.54

 conmigo

1.54

我的

1.53

my

1.50

 meine

1.44

 мной

1.43

 meiner

1.43

Activations Density 1.016%

concepts related to personal relationships and social interactions

No Comments

No Known Activations