INDEX

Explanations

phrases related to years and historical events

oai_token-act-pair · gpt-3.5-turbo

instances of dates paired with contextual information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

actions

-0.74

ACTION

-0.68

upp

-0.68

ahu

-0.67

edge

-0.66

Mods

-0.63

uch

-0.63

heter

-0.63

 antioxid

-0.61

Thumbnail

-0.61

POSITIVE LOGITS

 onwards

0.94

imester

0.76

BuyableInstoreAndOnline

0.72

ruary

0.72

ategory

0.71

 onward

0.69

bernatorial

0.67

Kad

0.66

Jah

0.65

 Reincarn

0.63

Activations Density 0.542%

phrases related to years and historical events

instances of dates paired with contextual information

No Comments

No Known Activations