INDEX

Explanations

types of entities in mathematical expressions or programming syntax

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

cré

-0.45

-0.44

or

-0.43

conditional

-0.43

to

-0.42

“

-0.42

рес

-0.41

 just

-0.41

{\

-0.41

bunga

-0.40

POSITIVE LOGITS

principalColumn

0.97

 تانيه

0.96

windowFixed

0.89

 propOrder

0.88

 Majefty

0.85

WebVitals

0.83

 Normdatei

0.82

oredCriteria

0.82

 pleaſure

0.80

AccessorTable

0.79

Activations Density 2.147%

types of entities in mathematical expressions or programming syntax

No Comments

No Known Activations