INDEX

Explanations

specific mentions of an item or object in a text

oai_token-act-pair · gpt-3.5-turbo

references to specific items or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

orks

-0.87

 Durham

-0.76

 Hess

-0.65

 Schro

-0.63

 Roads

-0.62

 Wilmington

-0.62

 Zimmer

-0.62

govern

-0.61

Ã±o

-0.60

 Telegram

-0.60

POSITIVE LOGITS

 item

1.05

item

1.04

 items

1.02

aclysm

0.91

iques

0.91

Items

0.91

Item

0.90

izer

0.89

items

0.86

abilia

0.86

Activations Density 0.012%

specific mentions of an item or object in a text

references to specific items or products

No Comments

No Known Activations