INDEX

Explanations

references to scientific articles and related metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 five

-1.07

 fifteen

-1.06

 Five

-1.05

 Fifteen

-1.03

Five

-0.98

five

-0.97

Fifteen

-0.96

Fifth

-0.94

 FIVE

-0.92

FIVE

-0.90

POSITIVE LOGITS

ValueStyle

0.53

 noqa

0.49

igshid

0.49

 sorter

0.48

yaf

0.48

attaa

0.47

θα

0.46

ornis

0.44

randir

0.44

 Biochem

0.44

Activations Density 0.287%

references to scientific articles and related metadata

No Comments

No Known Activations