INDEX

Explanations

references to mid-sized categories or intervals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

:✨

-0.78

']?>

-0.77

 uVar

-0.76

 Tavares

-0.73

таратура

-0.71

')]

-0.69

ので

-0.68

 Réponses

-0.68

Бахар

-0.66

%)$

-0.65

POSITIVE LOGITS

mid

2.33

Mid

2.27

Mid

2.23

MID

2.17

mid

2.08

MID

1.92

 mids

1.64

 Middel

1.51

 midterm

1.48

mids

1.46

Activations Density 0.044%

references to mid-sized categories or intervals

No Comments

No Known Activations