INDEX

Explanations

the word "naught" or variations of it

oai_token-act-pair · gpt-3.5-turbo

instances of the word "caught" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

br

-0.67

 hist

-0.66

 Section

-0.65

 ratings

-0.64

Kes

-0.63

 rating

-0.63

dil

-0.62

 mood

-0.61

 cellular

-0.61

Pie

-0.61

POSITIVE LOGITS

aught

4.38

ought

1.89

atching

1.24

augh

1.23

omore

0.97

urst

0.97

ook

0.97

oded

0.96

aughter

0.94

Lear

0.93

Activations Density 0.005%

the word "naught" or variations of it

instances of the word "caught" in various contexts

No Comments

No Known Activations