INDEX

Explanations

words and phrases relating to evaluation and analysis processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

writeField

-0.87

LookAnd

-0.74

MigrationBuilder

-0.72

ReusableCell

-0.69

CloseOperation

-0.69

 cref

-0.69

qrstuvwxyz

-0.67

featureID

-0.66

="@+

-0.63

GEBURTSDATUM

-0.63

POSITIVE LOGITS

 carefully

0.55

 Carefully

0.50

 Bourgoin

0.49

Faker

0.47

boho

0.46

zog

0.46

gens

0.45

 instead

0.45

 gens

0.44

 another

0.43

Activations Density 0.497%

words and phrases relating to evaluation and analysis processes

No Comments

No Known Activations