INDEX

Explanations

phrases indicating an addition or inclusion

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

CopyWith

-0.67

lgari

-0.60

rzost

-0.60

GraphicsUnit

-0.54

icose

-0.54

__;

-0.53

yyv

-0.50

ndice

-0.50

SequentialGroup

-0.50

kháu

-0.50

POSITIVE LOGITS

Jereo

0.60

sproz

0.59

 initComponents

0.58

ându

0.51

ьаж

0.51

Приятного

0.49

جغرافيا

0.49

reportWebVitals

0.47

 obvio

0.46

__':

0.45

Activations Density 0.456%

phrases indicating an addition or inclusion

No Comments

No Known Activations