INDEX

Explanations

terms related to programming and technical constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

^(@)

-1.64

NUMX

-1.59

 ་་

-1.50

$_"

-1.46

\<^

-1.42

>\<^

-1.42

 Мексичка

-1.38

DockStyle

-1.37

 tslint

-1.36

〢

-1.35

POSITIVE LOGITS

<eos>

1.77

↵↵

1.73

↵

1.66

1.56

1.37

1.35

↵↵↵

1.31

↵↵↵↵

1.24

–

1.23

1.18

Activations Density 2.617%

terms related to programming and technical constructs

No Comments

No Known Activations