INDEX

Explanations

It is looking for phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

the phrase that begins with the letter 'L' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Drawn

-0.83

 Antar

-0.79

oun

-0.74

 vulner

-0.70

 sacrific

-0.69

 seiz

-0.66

 Laurent

-0.66

IPM

-0.63

 Gael

-0.63

 Citiz

-0.63

POSITIVE LOGITS

little

0.90

href

0.87

same

0.86

ï¸ı

0.83

existence

0.82

could

0.82

mir

0.82

shall

0.81

something

0.81

ult

0.80

Activations Density 0.134%

It is looking for phrases indicating emphasis or importance

the phrase that begins with the letter 'L' in various contexts

No Comments

No Known Activations