INDEX

Explanations

terms related to risk factors and education 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 satunya

-0.80

aaral

-0.78

etc

-0.71

ActivityCompat

-0.71

wußt

-0.70

istoitu

-0.70

 jepang

-0.70

verhält

-0.68

kannt

-0.68

gründe

-0.67

POSITIVE LOGITS

1.46

-,

0.81

‑

0.79

—

0.74

expandindo

0.74

-/

0.73

-'

0.67

־

0.67

‐

0.62

Activations Density 0.913%

terms related to risk factors and education in various contexts

No Comments

No Known Activations