INDEX

Explanations

references to text-related programming elements or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Thema

-0.61

Rüyada

-0.60

^(@)

-0.60

Còn

-0.59

 Heilig

-0.58

feitura

-0.56

"]);

-0.56

%");

-0.55

ambién

-0.54

ximity

-0.54

POSITIVE LOGITS

Text

2.23

 Text

1.88

TEXT

1.33

 text

1.32

 TEXT

1.27

text

1.12

文本

1.06

Texts

1.03

 texts

1.02

 Texts

0.99

Activations Density 0.029%

references to text-related programming elements or libraries

No Comments

No Known Activations