INDEX

Explanations

phrases related to comparisons and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RetentionPolicy

-0.91

ItemBackground

-0.89

 propOrder

-0.89

principalTable

-0.87

 pleaſure

-0.86

 betweenstory

-0.85

 nakalista

-0.84

 myſelf

-0.83

 OnInit

-0.82

enderror

-0.80

POSITIVE LOGITS

 perhaps

0.53

 which

0.51

0.50

 notamment

0.47

Hozzáférés

0.46

0.45

Whilst

0.45

par

0.45

an

0.43

 magari

0.43

Activations Density 0.585%

phrases related to comparisons and conditions

No Comments

No Known Activations