INDEX

Explanations

ingredients or cooking-related words

oai_token-act-pair · gpt-3.5-turbo

references to various types of cooking oils and their uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

EMBER

-0.74

RON

-0.73

âĸ¬

-0.73

 Visitors

-0.72

BY

-0.68

Cox

-0.68

Jae

-0.67

èª

-0.66

ernaut

-0.65

 Chamberlain

-0.65

POSITIVE LOGITS

seed

1.17

 slic

1.02

 glands

0.96

tip

0.93

oil

0.86

brush

0.84

 gland

0.83

oil

0.82

lette

0.82

acid

0.81

Activations Density 0.016%

ingredients or cooking-related words

references to various types of cooking oils and their uses

No Comments

No Known Activations