INDEX

Explanations

mentions of "code" and its variations or descriptions in a technical context

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

{}\

-0.82

\"");

-0.77

 Majefty

-0.70

🏾

-0.70

 Thurston

-0.69

🏼

-0.69

 ſmall

-0.69

.\"

-0.69

 myſelf

-0.68

 preſent

-0.68

POSITIVE LOGITS

 codes

1.29

 Codes

1.26

CODE

1.21

code

1.19

codes

1.19

 CODE

1.18

 Code

1.18

 code

1.16

Cod

1.15

Codes

1.14

Activations Density 0.117%

mentions of "code" and its variations or descriptions in a technical context

No Comments

No Known Activations