INDEX

Explanations

specific references to drawable resources in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

parsedMessage

-1.14

 doInBackground

-1.13

HasForeignKey

-1.09

principalColumn

-1.08

+#+#

-1.08

 itſelf

-1.04

tagHelperRunner

-1.03

 '\\;'

-1.01

multer

-0.96

 tartalomajánló

-0.96

POSITIVE LOGITS

drawable

1.57

Drawable

0.92

mipmap

0.84

 drawable

0.76

Errorf

0.68

 Drawable

0.65

Fatalf

0.58

„

0.56

0.54

“

0.51

Activations Density 0.008%

specific references to drawable resources in code snippets

No Comments

No Known Activations