INDEX

Explanations

phrases indicating a lack of understanding or knowledge and a lack of desire to take responsibility

oai_token-act-pair · gpt-3.5-turbo

instances of a specific symbol or character

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ozy

-0.69

 Palest

-0.66

Tid

-0.62

BuyableInstoreAndOnline

-0.60

 juggling

-0.60

Buyable

-0.60

Sly

-0.59

Yor

-0.59

 Suzuki

-0.58

 paras

-0.58

POSITIVE LOGITS

¬

1.21

¼

1.21

ª

1.20

Ń

1.14

£

1.12

¤

1.09

Ĵ

1.09

Ķ

1.08

ĸ

1.08

ħ

1.07

Activations Density 0.161%

phrases indicating a lack of understanding or knowledge and a lack of desire to take responsibility

instances of a specific symbol or character

No Comments

No Known Activations