INDEX

Explanations

references to a person/entity named "Che"

oai_token-act-pair · gpt-3.5-turbo

the term "Che" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 illum

-0.72

ãĤ´ãĥ³

-0.71

Ã°

-0.69

nm

-0.69

arium

-0.67

æ©Ł

-0.67

atural

-0.65

paio

-0.63

 subdivision

-0.63

ERA

-0.63

POSITIVE LOGITS

Che

3.66

Che

2.55

che

1.82

che

1.69

Chel

1.52

 Chel

1.29

 Cheng

1.23

CH

1.18

Gro

1.17

 Chow

1.16

Activations Density 0.012%

references to a person/entity named "Che"

the term "Che" in various contexts

No Comments

No Known Activations