INDEX

Explanations

references to assessments and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

assertEqual

-0.52

zeć

-0.51

principalTable

-0.51

tvguidetime

-0.49

()?.

-0.48

URLException

-0.47

chaun

-0.47

();)

-0.46

 mengal

-0.46

DEG

-0.45

POSITIVE LOGITS

 насељу

0.58

brush

0.54

 MessageBoxIcon

0.53

kloped

0.53

 surla

0.52

ELTS

0.51

líben

0.50

 DialogInterface

0.50

 jLabel

0.49

łby

0.49

Activations Density 1.206%

references to assessments and evaluations

No Comments

No Known Activations