INDEX

Explanations

phrases indicating a reason or cause

oai_token-act-pair · gpt-3.5-turbo

instances of the word "because" indicating reasons or justifications

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

mint

-0.73

nin

-0.71

yan

-0.68

ries

-0.67

hal

-0.65

Scar

-0.65

wn

-0.63

Ku

-0.62

nex

-0.61

sey

-0.61

POSITIVE LOGITS

*/(

0.97

uristic

0.73

 they

0.69

 nobody

0.67

":"/

0.65

we

0.64

assetsadobe

0.64

urers

0.64

 there

0.64

uras

0.63

Activations Density 0.069%

phrases indicating a reason or cause

instances of the word "because" indicating reasons or justifications

No Comments

No Known Activations