INDEX

Explanations

terms and phrases related to databases and programming errors

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

ValueStyle

-0.60

ting

-0.58

mos

-0.56

lines

-0.55

ammlung

-0.53

RenderAtEndOf

-0.52

 complementa

-0.51

 provision

-0.51

ξεις

-0.50

beginPath

-0.47

POSITIVE LOGITS

uuuu

0.91

uuu

0.86

0.78

uuuuu

0.77

uu

0.70

COUVER

0.68

 AssemblyCompany

0.67

0.64

UUUU

0.60

du

0.57

Activations Density 0.402%

terms and phrases related to databases and programming errors

No Comments

No Known Activations