INDEX

Explanations

proper nouns related to individuals and organizations

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

 ་་

-0.81

 zelve

-0.81

 itſelf

-0.80

+#+#

-0.79

featureID

-0.74

CodedInputStream

-0.72

 bağlantılar

-0.72

TargetException

-0.71

 Normdatei

-0.70

󠁴

-0.69

POSITIVE LOGITS

bar

0.51

akt

0.50

LikeLike

0.48

голо

0.44

 said

0.43

κ

0.43

<eos>

0.42

 numerus

0.42

of

0.41

Activations Density 0.234%

proper nouns related to individuals and organizations

No Comments

No Known Activations