INDEX

Explanations

references to years

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BuyableInstoreAndOnline

-0.70

Urban

-0.67

Accessory

-0.67

Apr

-0.66

ebook

-0.65

Tier

-0.65

 Bought

-0.65

Zub

-0.64

coh

-0.63

 Barron

-0.60

POSITIVE LOGITS

 widest

0.70

 Strait

0.69

($)

0.68

hens

0.68

ueless

0.67

etheus

0.67

olesterol

0.66

minded

0.65

ommel

0.64

essed

0.64

Activations Density 0.000%

references to years

occurrences of the word "the."

No Comments

No Known Activations