INDEX

Explanations

terms related to scientific classification and taxonomy

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

鼓

-0.52

逼

-0.51

못

-0.50

 provinciale

-0.48

 bagay

-0.48

of

-0.48

 divertente

-0.47

 previous

-0.47

gefü

-0.47

 surprised

-0.47

POSITIVE LOGITS

aarrggbb

0.94

sizeCache

0.93

 MainAxisSize

0.90

 للمعارف

0.88

 صوتيه

0.88

+#+#

0.84

 تانيه

0.81

 виправивши

0.81

Personensuche

0.80

omiast

0.79

Activations Density 0.192%

terms related to scientific classification and taxonomy

No Comments

No Known Activations