INDEX

Explanations

references to statistical measures and their relevance to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

שְׁ

-0.61

δες

-0.60

bigoplus

-0.57

Tren

-0.55

 crystall

-0.54

krist

-0.54

𝙫

-0.54

 faſt

-0.53

 iſt

-0.53

Glas

-0.53

POSITIVE LOGITS

,-,

1.47

.$,

1.34

′,

1.26

°,

1.24

€,

1.24

 }}$,

1.23

++,

1.22

,<

1.21

=,

1.21

Activations Density 2.827%

references to statistical measures and their relevance to data analysis

No Comments

No Known Activations