INDEX

Explanations

numbers

oai_token-act-pair · gpt-3.5-turbo

references to numerical values and statistics

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

displayText

-0.71

henko

-0.68

 Collider

-0.65

HAM

-0.63

ULE

-0.63

 Loans

-0.61

ARI

-0.61

Interstitial

-0.61

misc

-0.60

 notor

-0.59

POSITIVE LOGITS

eteen

1.15

Eight

1.07

 thousand

1.04

irteen

1.03

 Shades

1.01

teen

0.99

eight

0.93

ifty

0.93

 Thousand

0.91

 percent

0.90

Activations Density 0.010%

numbers

references to numerical values and statistics

No Comments

No Known Activations