INDEX

Explanations

technical and programming-related terminology, particularly in assembly and data formats

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 situato

-0.51

قلال

-0.46

رها

-0.45

ONOM

-0.43

 sebab

-0.42

selectors

-0.42

 schrij

-0.42

trzyma

-0.42

人たち

-0.41

 kří

-0.41

POSITIVE LOGITS

BufferException

0.85

StoryboardSegue

0.81

AndEndTag

0.77

TargetException

0.76

0.75

 الحره

0.75

ArgsConstructor

0.73

UnusedPrivate

0.71

CppCodeGen

0.71

 <<<<<<<<<<<<<<

0.70

Activations Density 2.982%

technical and programming-related terminology, particularly in assembly and data formats

No Comments

No Known Activations