INDEX

Explanations

phrases indicating the prevalence or commonality of certain items or concepts

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

etje

-0.50

 which

-0.50

 baru

-0.45

ค์

-0.45

 déten

-0.43

soni

-0.43

校长

-0.43

Tracce

-0.43

tól

-0.43

 котором

-0.42

POSITIVE LOGITS

AndEndTag

0.98

 disambiguazione

0.93

FunctionFlags

0.86

المناصب

0.81

 كومونز

0.78

httphttps

0.77

PerformLayout

0.77

oredCriteria

0.75

RegressionTest

0.75

WithIOException

0.74

Activations Density 0.929%

phrases indicating the prevalence or commonality of certain items or concepts

No Comments

No Known Activations