INDEX

Explanations

terms related to technical devices and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.93

 spieg

-0.87

Datuak

-0.78

 UIImage

-0.77

 Ganes

-0.76

cam

-0.76

pheny

-0.75

alba

-0.75

 فار

-0.75

Kna

-0.74

POSITIVE LOGITS

Carole

0.81

---*/

0.78

 ***/

0.77

 SEDS

0.75

 setOpen

0.75

konomi

0.75

Ts

0.74

彡

0.72

]`

0.72

uminense

0.72

Activations Density 2.139%

terms related to technical devices and components

No Comments

No Known Activations