INDEX

Explanations

non-English characters in the text

oai_token-act-pair · gpt-3.5-turbo

the character "ľ" 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 @ 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

 condem

-0.75

raints

-0.74

 disadvant

-0.73

 hemor

-0.70

 Seym

-0.69

 Instr

-0.63

 womb

-0.62

 apes

-0.59

 misunder

-0.58

 unborn

-0.58

POSITIVE LOGITS

ï¸ı

1.20

âĶĢâĶĢ

1.05

âĸł

0.86

conom

0.86

ï¸

0.82

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.82

uthor

0.81

Â°

0.80

0.79

ł

0.79

Activations Density 0.190%

non-English characters in the text

the character "ľ" in various contexts

No Comments

No Known Activations