INDEX

Explanations

Scandinavian names or words containing the character "ö"

oai_token-act-pair · gpt-3.5-turbo

the word "för," which indicates discussions related to purpose or reason in Swedish

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Crusader

-0.70

 Watson

-0.69

 Bengal

-0.66

tons

-0.66

ORED

-0.63

INESS

-0.62

Sek

-0.61

corn

-0.61

enegger

-0.60

 Blacks

-0.60

POSITIVE LOGITS

andom

1.12

Ã¶r

0.91

Ã¶

0.90

Ã°

0.89

onto

0.83

Ã¶n

0.81

Ã¡n

0.79

Ã¼

0.79

rent

0.79

istani

0.77

Activations Density 0.010%

Scandinavian names or words containing the character "ö"

the word "för," which indicates discussions related to purpose or reason in Swedish

No Comments

No Known Activations