INDEX

Explanations

names or terms that indicate geographic locations or topographical features

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

 Offisielt

-0.79

 itſelf

-0.79

 fubject

-0.78

Tembelea

-0.76

 himſelf

-0.76

 poffe

-0.76

 Shakspeare

-0.75

ammans

-0.74

 metropolitana

-0.74

 Audiodateien

-0.74

POSITIVE LOGITS

 '\\;'

0.60

BeginInit

0.53

Gweler

0.51

ous

0.49

et

0.48

0.47

Спасылкі

0.46

oko

0.46

PYX

0.46

inc

0.45

Activations Density 0.173%

names or terms that indicate geographic locations or topographical features

No Comments

No Known Activations