INDEX

Explanations

tokens indicating frequencies or repetitions within a structured context

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

ItemBackground

-0.80

aarrggbb

-0.65

 heuti

-0.63

bukkit

-0.61

 IndexPath

-0.60

存于互联网档案馆

-0.60

//

-0.60

imageshack

-0.60

 сельского

-0.59

UserScript

-0.59

POSITIVE LOGITS

 recently

0.62

 yılında

0.59

 gerçekleşti

0.55

SequentialGroup

0.55

ついに

0.54

日に

0.53

recently

0.52

 officially

0.52

mosis

0.51

 недавно

0.51

Activations Density 0.172%

tokens indicating frequencies or repetitions within a structured context

No Comments

No Known Activations