INDEX

Explanations

instances of closing brackets or quotation marks in documentation or code contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

fromnode

-0.68

 gagné

-0.67

 battre

-0.65

 préféré

-0.64

ThemeOverlay

-0.64

 convaincre

-0.63

seamnă

-0.61

gameserver

-0.61

writeHead

-0.60

 Channing

-0.57

POSITIVE LOGITS

 يتيمه

0.87

 nahilalakip

0.80

 utafitiHapana

0.77

WriteTagHelper

0.77

AccessorTable

0.67

0.65

 تانيه

0.61

ArgsConstructor

0.60

ContentAsync

0.57

Activations Density 0.080%

instances of closing brackets or quotation marks in documentation or code contexts

No Comments

No Known Activations