INDEX

Explanations

phrases related to conspiracy or hidden collaboration

oai_token-act-pair · gpt-3.5-turbo

references to consular actions or permissions

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

 oats

-0.75

lihood

-0.69

 Carnegie

-0.68

shire

-0.67

 Shoals

-0.66

 Clover

-0.66

 Hills

-0.65

 derby

-0.65

baugh

-0.65

 Lakes

-0.65

POSITIVE LOGITS

cription

1.08

cript

1.06

idered

1.04

cientious

1.03

oled

1.00

cient

0.96

oling

0.95

ensual

0.93

pired

0.93

ented

0.93

Activations Density 0.008%

phrases related to conspiracy or hidden collaboration

references to consular actions or permissions

No Comments

No Known Activations