INDEX

Explanations

specific identifiers or codes related to programming or 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 @ 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

-0.71

-0.59

-0.57

al

-0.56

-0.49

ią

-0.48

ovo

-0.48

-0.47

ی

-0.47

lus

-0.47

POSITIVE LOGITS

 كومونز

1.01

TargetException

1.01

DockStyle

0.97

IsContent

0.96

 cherchés

0.93

Tikang

0.92

sizeCache

0.88

脚注の使い方

0.88

WriteBarrier

0.86

ArgsConstructor

0.86

Activations Density 0.384%

specific identifiers or codes related to programming or data structures

No Comments

No Known Activations