INDEX

Explanations

instances of structured text or lists related to procedural information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

NUMX

-1.08

^(@)

-1.02

 صوتيه

-0.94

abetes

-0.94

 FetchType

-0.93

 useAuth

-0.91

—

-0.90

HasForeignKey

-0.89

nologue

-0.86

 NSCoder

-0.86

POSITIVE LOGITS

↵↵

1.27

<eos>

1.16

↵

0.99

0.94

↵↵↵

0.85

↵↵↵↵

0.76

。

0.75

In

0.74

<bos>

0.73

).

0.73

Activations Density 0.047%

instances of structured text or lists related to procedural information

No Comments

No Known Activations