INDEX

Explanations

phrases indicating certainty or determination

oai_token-act-pair · gpt-3.5-turbo

statements indicating personal opinions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 constituted

-0.78

 varied

-0.75

 differed

-0.72

 encomp

-0.69

 disparate

-0.68

 incorporated

-0.67

 millenn

-0.66

 aggregate

-0.65

 accumulated

-0.65

 dispersed

-0.65

POSITIVE LOGITS

He

1.72

His

1.61

He

1.58

his

1.52

His

1.39

he

1.39

he

1.35

him

1.32

HIS

1.18

his

1.18

Activations Density 0.691%

phrases indicating certainty or determination

statements indicating personal opinions or sentiments

No Comments

No Known Activations