INDEX

Explanations

patterns or sequences of repeated characters and symbols

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

-0.56

Население

-0.55

...

-0.54

roppo

-0.53

-0.51

-0.50

-0.48

lo

-0.48

mHandler

-0.48

aurus

-0.47

POSITIVE LOGITS

 autorytatywna

0.93

 utafitiHapana

0.88

 متعلقه

0.85

 للاسماء

0.83

 ſche

0.80

 AssemblyTitle

0.75

 Houſe

0.72

ſelf

0.72

 Reſ

0.72

 تضيفلها

0.71

Activations Density 0.269%

patterns or sequences of repeated characters and symbols

No Comments

No Known Activations