INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or letter 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 disadvant

-0.76

 Palestin

-0.72

 mathemat

-0.71

 lawy

-0.66

 contrace

-0.63

 misunder

-0.62

 fortun

-0.62

 incorpor

-0.62

 Instr

-0.62

 obser

-0.61

POSITIVE LOGITS

ï¸ı

1.22

ï¸

0.87

Balt

0.78

âĶĢâĶĢ

0.75

âĻ

0.74

âĹ

0.73

tre

0.69

âĸł

0.69

eric

0.68

Â£

0.68

Activations Density 0.334%

people's names

instances of a specific character or letter in the text

No Comments

No Known Activations