INDEX

Explanations

words related to performance or achievement metrics

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

MLLoader

-0.49

nos

-0.47

 TestBed

-0.45

tgärder

-0.45

しく

-0.44

 request

-0.44

 <<<<<<<<<<<<<<

-0.43

zd

-0.42

derd

-0.42

ell

-0.41

POSITIVE LOGITS

 career

0.70

Personensuche

0.67

Portale

0.66

career

0.65

Portály

0.61

 ویکی‌پدی

0.58

 agrí

0.58

encodeWith

0.58

opportunity

0.58

PreExecute

0.57

Activations Density 0.526%

words related to performance or achievement metrics

No Comments

No Known Activations