INDEX

Explanations

various forms of underscores and underscores followed by numbers, likely indicating placeholders or variable names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

存于互联网档案馆

-0.78

 виправивши

-0.71

 CommonModule

-0.70

 XNUMX

-0.69

 consultato

-0.67

interopRequire

-0.66

 Accesat

-0.64

 itſelf

-0.62

-)

-0.62

.")]

-0.61

POSITIVE LOGITS

1.29

0.90

._

0.80

__

0.77

}_

0.74

_[

0.73

\_

0.71

_.

0.68

_{

0.65

_(

0.65

Activations Density 0.698%

various forms of underscores and underscores followed by numbers, likely indicating placeholders or variable names

No Comments

No Known Activations