INDEX

Explanations

variations of the prefix "ab" in different contexts

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

 ?>">

-0.82

";}

-0.82

ագրություններ

-0.79

 Vesu

-0.77

</h5>

-0.77

 Deniz

-0.76

 Argos

-0.76

IDR

-0.76

"]]

-0.76

")]

-0.75

POSITIVE LOGITS

Ab

2.28

ab

2.27

Ab

2.03

AB

1.96

ab

1.83

AB

1.61

 abzu

1.34

 Аб

1.28

 Abby

1.26

 ablation

1.26

Activations Density 0.070%

variations of the prefix "ab" in different contexts

No Comments

No Known Activations