INDEX

Explanations

mentions of methodologies related to data analysis and calibration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.52

 showcasing

-0.51

tagHelperRunner

-0.49

XtraGrid

-0.47

 diversify

-0.47

 Manifest

-0.47

 resourceCulture

-0.46

demik

-0.46

 Perfor

-0.44

://"

-0.44

POSITIVE LOGITS

 determination

1.25

 estimate

1.21

 estimates

1.17

 calculated

1.13

 estimation

1.07

 determined

1.06

 estimated

1.05

 Determination

1.04

 computed

1.03

Determination

1.02

Activations Density 2.034%

mentions of methodologies related to data analysis and calibration

No Comments

No Known Activations