INDEX

Explanations

statements or expressions related to personal feelings and self-perception

oai_token-act-pair · gpt-3.5-turbo

specific publication dates or timestamps

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

è¦ļéĨĴ

-0.82

 Ange

-0.69

ensional

-0.68

 GROUP

-0.66

 Spiel

-0.64

ometimes

-0.64

 WRITE

-0.63

å§«

-0.63

illac

-0.62

 Chaser

-0.61

POSITIVE LOGITS

ocity

0.65

 grav

0.65

nov

0.65

joy

0.64

 Dragonbound

0.64

Ub

0.63

atures

0.62

POL

0.62

orum

0.61

oken

0.60

Activations Density 0.000%

statements or expressions related to personal feelings and self-perception

specific publication dates or timestamps

No Comments

No Known Activations