INDEX

Explanations

terms and elements related to programming and computational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

teady

-0.45

iseaux

-0.42

rückt

-0.41

řád

-0.40

he

-0.39

 capo

-0.39

 xét

-0.39

 they

-0.38

hitheatre

-0.38

 Beine

-0.37

POSITIVE LOGITS

styleType

1.04

sizeCache

0.99

TypedDataSet

0.99

 Chwiliwch

0.94

 unknownFields

0.92

 चीज़ों

0.90

CodeAttribute

0.87

contentLoaded

0.87

 ddelweddau

0.86

oredCriteria

0.85

Activations Density 2.354%

terms and elements related to programming and computational structures

No Comments

No Known Activations