INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character 'Ļ' in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 mathemat

-0.81

 filler

-0.78

 fodder

-0.77

 recycling

-0.76

 incorpor

-0.74

 disadvant

-0.73

 pulp

-0.73

 chunks

-0.72

geries

-0.72

 thwart

-0.72

POSITIVE LOGITS

ï¸ı

1.79

 âĢº

1.31

âĢ

1.26

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

1.17

à¥

1.13

âĶĢâĶĢâĶĢâĶĢ

1.10

âĸ¬âĸ¬

1.06

à¼

1.06

âĸł

1.05

(@

1.05

Activations Density 0.172%

proper nouns

occurrences of the character 'Ļ' in the text

No Comments

No Known Activations