INDEX

Explanations

lines of code containing modifiers indicating the level of access for classes or methods

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

The token "final"

np_acts-logits-general · gemini-2.0-flash

static final

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

Билгалдахарш

-0.64

Története

-0.57

ftagPool

-0.57

 发表于

-0.57

CopyWith

-0.55

ContentAsync

-0.55

Soon

-0.54

hombres

-0.54

 ligiloj

-0.52

Péri

-0.51

POSITIVE LOGITS

 final

2.51

final

2.33

 Final

1.75

 FINAL

1.72

Final

1.72

FINAL

1.58

 finalised

1.27

 fina

1.25

 finals

1.22

 finalized

1.22

Activations Density 0.052%

lines of code containing modifiers indicating the level of access for classes or methods

The token "final"

static final

No Comments

No Known Activations