INDEX

Explanations

references to individuals or entities associated with the name "Ra."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 محفوظة

-0.76

TimeUnit

-0.61

 zich

-0.60

ending

-0.59

nment

-0.55

hemia

-0.54

IDATE

-0.53

 part

-0.51

rne

-0.51

iedades

-0.50

POSITIVE LOGITS

Rak

0.74

Rak

0.72

 Bradbury

0.72

contentLoaded

0.71

ra

0.70

Rau

0.68

Rac

0.68

 radians

0.68

 Rack

0.66

Ra

0.66

Activations Density 0.204%

references to individuals or entities associated with the name "Ra."

No Comments

No Known Activations