INDEX

Explanations

references to phases in various contexts, particularly related to processes, formulations, or stages of a study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

HOL

-0.54

uscular

-0.54

WritableDatabase

-0.52

inges

-0.52

Ho

-0.52

IFY

-0.51

ficulty

-0.50

ings

-0.50

couv

-0.49

gtest

-0.49

POSITIVE LOGITS

phase

0.88

 phase

0.80

 PHASE

0.78

PHASE

0.74

 phasing

0.73

 iſt

0.72

 itſelf

0.71

contentLoaded

0.70

Emp

0.69

 raiſ

0.69

Activations Density 0.169%

references to phases in various contexts, particularly related to processes, formulations, or stages of a study

No Comments

No Known Activations