INDEX

Explanations

numerical values associated with specific identifiers or keys in data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

setVerticalGroup

-0.63

 AssemblyCulture

-0.59

UnitTesting

-0.58

 ModelExpression

-0.56

 CreateTagHelper

-0.52

 springfox

-0.51

клопе

-0.49

ClientSize

-0.49

 HttpNotFound

-0.49

arkov

-0.48

POSITIVE LOGITS

 Савезне

0.71

省市镇

0.61

HostException

0.54

########.

0.52

ENDIF

0.50

 Paglinawan

0.50

couple

0.49

reportWebVitals

0.49

 lumières

0.48

---*/

0.48

Activations Density 1.522%

numerical values associated with specific identifiers or keys in data structures

No Comments

No Known Activations