INDEX

Explanations

phrases indicating dependency or conditions in programming and configuration contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AutoSize

-0.47

var

-0.45

fl

-0.43

 épaules

-0.43

for

-0.42

config

-0.42

’

-0.42

<code>

-0.41

```

-0.41

POSITIVE LOGITS

 nakalista

0.85

 تضيفلها

0.82

MENAFN

0.80

<bos>

0.79

zące

0.72

 getById

0.70

leſs

0.69

OLOGIES

0.67

brainly

0.65

archiviato

0.64

Activations Density 1.922%

phrases indicating dependency or conditions in programming and configuration contexts

No Comments

No Known Activations