INDEX

Explanations

types or categories of different items or concepts

oai_token-act-pair · gpt-3.5-turbo

references to groupings or categorizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

brance

-0.88

ortium

-0.65

potion

-0.64

$$

-0.64

abuse

-0.63

hire

-0.63

haw

-0.63

displayText

-0.62

atown

-0.62

luck

-0.61

POSITIVE LOGITS

 phases

1.34

 main

1.34

 kinds

1.30

 types

1.29

 distinct

1.28

 tiers

1.21

 categories

1.20

 pillars

1.19

 modes

1.16

 stages

1.11

Activations Density 0.141%

types or categories of different items or concepts

references to groupings or categorizations

No Comments

No Known Activations