INDEX

Explanations

instances of the word "within" and variations of it, suggesting it detects discussions about containment or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

er

-0.77

-0.69

cy

-0.69

lar

-0.69

io

-0.69

es

-0.67

-0.65

گ

-0.64

pep

-0.64

ar

-0.63

POSITIVE LOGITS

within

1.85

 Within

1.82

Within

1.78

 within

1.72

 WITHIN

1.72

 InputDecoration

1.25

 binnen

1.23

 entro

1.12

 innerhalb

1.12

 dentro

1.09

Activations Density 0.080%

instances of the word "within" and variations of it, suggesting it detects discussions about containment or context

No Comments

No Known Activations