INDEX

Explanations

the occurrences of the word "Ren," likely related to a concept or person in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

oredCriteria

-0.76

AndEndTag

-0.67

NameInMap

-0.66

 виправивши

-0.65

 defaultstate

-0.64

 nahilalakip

-0.60

Obrázky

-0.58

 kaarangay

-0.57

VersionUID

-0.57

UnknownFields

-0.54

POSITIVE LOGITS

 torch

0.86

Torch

0.74

 Torch

0.73

torch

0.69

пература

0.67

NUMX

0.65

 Houſe

0.63

++]

0.59

 myſelf

0.58

 Anſ

0.57

Activations Density 0.115%

the occurrences of the word "Ren," likely related to a concept or person in the text

No Comments

No Known Activations