INDEX

Explanations

instances of the name or generic reference to various subjects, potentially related to organizations or events

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

rungsseite

-0.65

Tikang

-0.58

tvguidetime

-0.56

Portály

-0.56

Dobrý

-0.55

RegressionTest

-0.52

 AssemblyCulture

-0.51

 EconPapers

-0.49

Ahoj

-0.49

 '\\;'

-0.49

POSITIVE LOGITS

Datuak

0.67

↵

0.62

MigrationBuilder

0.60

</u>

0.57

↵↵↵↵

0.56

↵↵↵

0.55

 Wicidata

0.53

axx

0.52

çants

0.51

 HasFactory

0.50

Activations Density 0.087%

instances of the name or generic reference to various subjects, potentially related to organizations or events

No Comments

No Known Activations