INDEX

Explanations

repeated mentions and references to "contents" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.81

-0.77

the

-0.71

↵↵

-0.70

-0.69

in

-0.69

-0.68

se

-0.68

POSITIVE LOGITS

 ainfi

0.90

 queſta

0.90

 zijne

0.85

 vectorielle

0.85

 mijne

0.85

 læng

0.82

 avoient

0.81

 étoient

0.81

$_"

0.81

 varandra

0.78

Activations Density 0.557%

repeated mentions and references to "contents" in various contexts

No Comments

No Known Activations