INDEX

Explanations

references to specific people or entities in various 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

 greateſt

-0.80

 iſt

-0.78

Efq

-0.73

Eſ

-0.71

 Diſ

-0.71

 Majefty

-0.71

 Houſe

-0.70

 ſche

-0.68

 ―――――

-0.67

 Anſ

-0.67

POSITIVE LOGITS

andExpect

0.63

Contribute

0.57

InlineData

0.55

LookAnd

0.54

 nahilalakip

0.49

 pinulongan

0.47

AddHtmlAttribute

0.47

 Мексичка

0.47

esercito

0.46

CONSIN

0.45

Activations Density 0.818%

references to specific people or entities in various contexts

No Comments

No Known Activations