INDEX

Explanations

references to structured formats, data, or programming-related terms

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

-0.98

-0.91

-0.85

-0.82

-0.81

-0.80

POSITIVE LOGITS

 feroit

1.03

 enfans

0.98

 auroit

0.96

 avoient

0.93

 pouvoit

0.90

 étoit

0.86

 étoient

0.84

 ainfi

0.79

 desmotivaciones

0.74

 nôtre

0.72

Activations Density 4.984%

references to structured formats, data, or programming-related terms

No Comments

No Known Activations