INDEX

Explanations

mathematical concepts and terminology related to sets and operations on them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 متعلقه

-0.79

 سكانية

-0.78

twimg

-0.67

HasBeenSet

-0.66

writeFieldEnd

-0.64

basicConfig

-0.62

RTEX

-0.62

ukkig

-0.60

-------------</

-0.60

ingway

-0.59

POSITIVE LOGITS

 denominada

0.93

 denominado

0.85

 llamada

0.85

 called

0.82

 llamado

0.76

called

0.73

‘

0.71

“

0.71

 llamadas

0.69

 chamada

0.69

Activations Density 1.407%

mathematical concepts and terminology related to sets and operations on them

No Comments

No Known Activations