INDEX

Explanations

variables, particularly those related to indexing or iteration within loops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

↵↵

-0.51

 disambiguazione

-0.45

hbs

-0.42

↵

-0.42

Sooo

-0.42

 Winaray

-0.41

 dens

-0.41

енча

-0.40

oooooo

-0.40

fü

-0.39

POSITIVE LOGITS

VersionUID

1.04

 MainAxisSize

0.91

AxisAlignment

0.90

SBATCH

0.90

complexContent

0.87

########.

0.76

NUMX

0.76

WaitGroup

0.76

 كومونز

0.76

 IndexPath

0.74

Activations Density 0.022%

variables, particularly those related to indexing or iteration within loops

No Comments

No Known Activations