INDEX

Explanations

concepts related to loss, negotiation, and ambiguity in various contexts

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

ⓧ

-0.55

olarmente

-0.55

ExtendWith

-0.52

discriminator

-0.51

 חיצוניים

-0.50

InjectAttribute

-0.49

apimachinery

-0.48

kozá

-0.48

IRST

-0.46

帖最后由

-0.46

POSITIVE LOGITS

able

2.25

ABLE

1.83

ables

1.57

ability

1.56

nable

1.44

eable

1.42

 able

1.38

pable

1.37

Able

1.35

lable

1.32

Activations Density 0.251%

concepts related to loss, negotiation, and ambiguity in various contexts

No Comments

No Known Activations