INDEX

Explanations

prominent numerical values and their relationships within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nahilalakip

-0.69

transQ

-0.67

 braccia

-0.65

webElement

-0.65

 GenerationType

-0.64

 noDo

-0.64

}))

-0.61

UnsafeEnabled

-0.60

pushFollow

-0.60

>{@

-0.59

POSITIVE LOGITS

0.71

enumi

0.68

]='\

0.62

########.

0.61

]--;

0.59

sue

0.58

&=&

0.58

/~

0.58

 fold

0.57

pital

0.57

Activations Density 0.525%

prominent numerical values and their relationships within the text

No Comments

No Known Activations