INDEX

Explanations

phrases related to transitions or changes in state

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

bula

-0.46

円

-0.41

장

-0.38

chond

-0.38

es

-0.38

 làm

-0.38

варь

-0.38

bulo

-0.37

 imidlertid

-0.37

คำ

-0.37

POSITIVE LOGITS

 Majefty

1.02

 Monfieur

0.94

CloseOperation

0.91

 pleaſure

0.90

 myſelf

0.88

 ſeveral

0.88

ſelf

0.88

 itſelf

0.83

IsPostBack

0.83

ſelves

0.82

Activations Density 0.373%

phrases related to transitions or changes in state

No Comments

No Known Activations