INDEX

Explanations

conditional phrases and programming instructions

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

หนึ่ง

-0.59

Παραπομπές

-0.54

 kasarigan

-0.52

 BorderRadius

-0.48

"]').

-0.48

}`).

-0.48

Aiheesta

-0.48

 GetEnumerator

-0.47

TagMode

-0.46

spesies

-0.46

POSITIVE LOGITS

StructEnd

0.70

AutoField

0.59

ulemon

0.57

basicConfig

0.56

divarius

0.55

тивность

0.55

hoeddwyd

0.55

findpost

0.55

owulf

0.54

 Norvège

0.53

Activations Density 0.038%

conditional phrases and programming instructions

No Comments

No Known Activations