INDEX

Explanations

code snippets or references in programming contexts

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

-0.57

-0.56

“

-0.55

-0.54

and

-0.52

—

-0.49

dis

-0.48

-0.47

--

-0.46

POSITIVE LOGITS

تقاوى

1.06

rungsseite

1.04

tvguidetime

1.00

GEBURTSDATUM

0.99

 ExecuteAsync

0.96

 дописавши

0.96

 AssemblyTitle

0.86

expandindo

0.85

 ostavi

0.84

 fathoms

0.83

Activations Density 0.208%

code snippets or references in programming contexts

No Comments

No Known Activations