INDEX

Explanations

conjunctions and phrases indicating relationships or conditions

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

IntoConstraints

-0.88

Personensuche

-0.80

دانشنامهٔ

-0.77

MfG

-0.76

EDEFAULT

-0.74

LookAnd

-0.72

MigrationBuilder

-0.72

NameInMap

-0.69

dymyr

-0.69

iNdEx

-0.68

POSITIVE LOGITS

 that

0.97

 bahwa

0.84

 ότι

0.77

 bahawa

0.74

 there

0.73

that

0.71

 faptul

0.64

że

0.61

 THAT

0.60

 dass

0.60

Activations Density 0.353%

conjunctions and phrases indicating relationships or conditions

No Comments

No Known Activations