INDEX

Explanations

programming and programming-related constructs in 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 tartalomajánló

-0.69

 EClass

-0.68

verwijspagina

-0.67

μβρίου

-0.65

 سكانية

-0.63

rungsseite

-0.63

 мәкал

-0.63

≦)

-0.63

cookieParser

-0.62

antMatchers

-0.61

POSITIVE LOGITS

<strong>

0.66

//

0.63

<b>

0.62

0.61

()]

0.55

///

0.52

amint

0.50

[toxicity=0]

0.50

Activations Density 0.099%

programming and programming-related constructs in the text

No Comments

No Known Activations