INDEX

Explanations

proper nouns, particularly names and places associated with legal and historical contexts

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

 Sarmiento

-0.79

//$

-0.72

 charité

-0.69

([\

-0.69

nebago

-0.68

 QString

-0.68

Становништво

-0.67

ASF

-0.67

 cartões

-0.66

]='\

-0.66

POSITIVE LOGITS

üten

0.71

✨:

0.71

 gradients

0.68

 gradient

0.66

subsec

0.65

Dew

0.65

 Gradient

0.64

 Coordin

0.64

 Spri

0.64

 Prä

0.63

Activations Density 2.525%

proper nouns, particularly names and places associated with legal and historical contexts

No Comments

No Known Activations