INDEX

Explanations

references to the letter "F" followed by a single character or word

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'F' 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 @ 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

vier

-0.73

 Aether

-0.67

 Reborn

-0.66

 Twain

-0.65

 Hole

-0.65

 Conquest

-0.64

 Sapphire

-0.64

 Hades

-0.64

 Miko

-0.63

 mater

-0.63

POSITIVE LOGITS

ortun

1.29

ocused

1.27

ortunate

1.22

ocusing

1.22

ruits

1.21

avour

1.21

ertility

1.18

reet

1.15

OUND

1.13

AST

1.13

Activations Density 0.058%

references to the letter "F" followed by a single character or word

instances of the letter 'F' in various contexts

No Comments

No Known Activations