INDEX

Explanations

words related to political discussions or agreements

oai_token-act-pair · gpt-3.5-turbo

specific segments of text containing the character “Ļ.”

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

 emphasis

-0.73

 demand

-0.67

 market

-0.65

isation

-0.63

ised

-0.62

 syndrome

-0.61

ises

-0.60

 capacity

-0.59

Equ

-0.59

 Crom

-0.59

POSITIVE LOGITS

Ļ

4.35

ĺ

1.81

Ľ

1.79

ħ

1.78

©

1.73

Ĺ

1.71

ļ

1.70

ľ

1.68

ĳ

1.68

ķ

1.67

Activations Density 0.706%

words related to political discussions or agreements

specific segments of text containing the character “Ļ.”

No Comments

No Known Activations