INDEX

Explanations

dates related to the year 2017

oai_token-act-pair · gpt-3.5-turbo

references to the year 2017

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

tub

-0.75

cephal

-0.74

 drowned

-0.70

imore

-0.63

vere

-0.63

 pals

-0.61

osp

-0.61

anguage

-0.60

 snipp

-0.60

llular

-0.59

POSITIVE LOGITS

å¹

0.88

âĢ²

0.81

ESV

0.76

0.70

 Remastered

0.69

 onwards

0.68

âĢ³

0.68

0.67

 Odyssey

0.66

âĨĳ

0.66

Activations Density 0.038%

dates related to the year 2017

references to the year 2017

No Comments

No Known Activations