INDEX

Explanations

references to groups or categories related to demographics and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ah

-0.44

 olan

-0.43

 busto

-0.43

ugy

-0.43

tua

-0.42

 recenti

-0.41

 Administrativna

-0.41

悍

-0.39

uh

-0.39

Ra

-0.39

POSITIVE LOGITS

 itſelf

1.02

 فريبيس

0.97

 doubtnut

0.91

 themſelves

0.88

 الحره

0.87

SWR

0.84

kloped

0.80

AxisAlignment

0.79

Efq

0.78

 uſe

0.77

Activations Density 0.521%

references to groups or categories related to demographics and statistics

No Comments

No Known Activations