INDEX

Explanations

instances and references to "code" within a technical or computational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 juſt

-0.65

__':

-0.63

 Majefty

-0.63

يميديا

-0.60

BagLayout

-0.60

 Reverso

-0.60

 poffe

-0.60

.\"

-0.59

ucun

-0.58

 ſeveral

-0.58

POSITIVE LOGITS

 codes

1.34

 Codes

1.26

 code

1.25

 CODE

1.19

code

1.16

codes

1.14

 Code

1.14

CODE

1.13

Codes

1.08

Code

1.06

Activations Density 0.105%

instances and references to "code" within a technical or computational context

No Comments

No Known Activations