INDEX

Explanations

JavaScript files with high activations

oai_token-act-pair · gpt-3.5-turbo

references to JavaScript files and modules

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lain

-0.77

 Staples

-0.74

 Fukushima

-0.68

 Soviets

-0.67

 Sinclair

-0.64

 Cheong

-0.62

liest

-0.61

 pressures

-0.61

places

-0.61

 Kubrick

-0.60

POSITIVE LOGITS

ullivan

1.20

uration

1.02

opher

0.90

inx

0.89

ESSION

0.88

ession

0.86

avascript

0.84

ophers

0.84

ocket

0.81

ames

0.80

Activations Density 0.017%

JavaScript files with high activations

references to JavaScript files and modules

No Comments

No Known Activations