INDEX

Explanations

repeated usage of the word "going."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 fubject

-0.77

 חיצוניים

-0.75

ekš

-0.72

 themſelves

-0.71

BagConstraints

-0.70

volezza

-0.67

 anhänger

-0.67

 herren

-0.65

máscara

-0.65

 Montaigne

-0.65

POSITIVE LOGITS

 going

1.90

 Going

1.77

 GOING

1.71

going

1.67

Going

1.67

GOING

1.47

 goin

1.35

goin

1.11

 Gonna

1.00

 coming

0.98

Activations Density 0.042%

repeated usage of the word "going."

No Comments

No Known Activations