INDEX

Explanations

terms and language related to assessment and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 utafitiHapana

-0.70

 quelquefois

-0.59

 sortant

-0.56

 Kaka

-0.55

 strå

-0.55

 quelcon

-0.55

 quelconque

-0.55

 ceramica

-0.53

NUMX

-0.52

 autocorrelation

-0.52

POSITIVE LOGITS

 EconPapers

0.75

jsxFileName

0.74

 pinulongan

0.71

 kasarigan

0.70

ConstraintMaker

0.69

FunctionFlags

0.68

TagMode

0.67

########.

0.65

:✨

0.64

 صوتيه

0.63

Activations Density 0.683%

terms and language related to assessment and evaluation

No Comments

No Known Activations