INDEX

Explanations

technical or programming-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.57

 from

-0.50

-0.48

to

-0.47

by

-0.46

in

-0.45

-0.44

-0.43

POSITIVE LOGITS

 ProtoMessage

2.76

GEBURTSDATUM

2.76

 nahilalakip

2.72

 autorytatywna

2.71

webElementXpaths

2.70

MigrationBuilder

2.66

WithIOException

2.66

LookAnd

2.65

SourceChecksum

2.56

NameInMap

2.51

Activations Density 0.080%

technical or programming-related terms and structures

No Comments

No Known Activations