INDEX

Explanations

phrases or references to authors and their publications

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

脚注の使い方

-0.74

 '\\;'

-0.70

észetes

-0.70

thâu

-0.69

انيف

-0.67

]='\

-0.64

)];

-0.61

teau

-0.61

الإنجليزية

-0.60

يطاليا

-0.58

POSITIVE LOGITS

tagHelperRunner

0.54

 ***!

0.46

imgur

0.45

 olun

0.43

ponses

0.42

 Оно

0.42

MockMvc

0.41

ConstraintMaker

0.41

 دیگری

0.40

 vicin

0.40

Activations Density 0.083%

phrases or references to authors and their publications

No Comments

No Known Activations