INDEX

Explanations

instances of the word "Two" followed by numbers representing a pair or group of items

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Two."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 guiActiveUnfocused

-0.75

omo

-0.74

 surroundings

-0.72

oper

-0.71

Ïī

-0.71

 widest

-0.70

employment

-0.67

ifice

-0.67

ordering

-0.64

activity

-0.64

POSITIVE LOGITS

teen

1.21

een

1.16

 Months

0.98

 Ways

0.95

 Hundred

0.91

 Weeks

0.89

Thirty

0.86

 Thousand

0.85

 Hours

0.84

eteen

0.82

Activations Density 0.071%

instances of the word "Two" followed by numbers representing a pair or group of items

occurrences of the word "Two."

No Comments

No Known Activations