INDEX

Explanations

contractions

oai_token-act-pair · gpt-3.5-turbo

negative statements or denials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Tokens

-0.77

åĮ

-0.71

GBT

-0.69

SpaceEngineers

-0.69

accompan

-0.69

Balance

-0.68

LED

-0.68

EMBER

-0.67

 millenn

-0.66

Someone

-0.65

POSITIVE LOGITS

ashtra

0.75

 Tsarnaev

0.68

 Mush

0.68

 Sere

0.68

notations

0.67

Rez

0.66

 Chess

0.61

 Eliot

0.61

 Phant

0.61

 Verb

0.60

Activations Density 0.435%

contractions

negative statements or denials

No Comments

No Known Activations