INDEX

Explanations

the symbols 'Ļ' and 'Ċ'

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol

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

 circulation

-0.66

 intercepted

-0.66

 litter

-0.65

 scattering

-0.63

 Palestin

-0.62

 captives

-0.61

 dossier

-0.60

 retrieval

-0.60

 thwarted

-0.60

 looms

-0.60

POSITIVE LOGITS

ï¸ı

1.39

ï¸

1.06

Â¯

0.86

laughs

0.85

Balt

0.83

âĶĢâĶĢâĶĢâĶĢ

0.80

âĶĢ

0.80

ðŁĺ

0.79

âĶĢâĶĢ

0.79

âĹ

0.79

Activations Density 0.659%

the symbols 'Ļ' and 'Ċ'

instances of a specific character or symbol

No Comments

No Known Activations