INDEX

Explanations

proper nouns or names ending with the letter 'K'

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 wide

-0.74

assetsadobe

-0.68

 ......

-0.65

Voc

-0.65

 âĢº

-0.62

(?,

-0.61

 ______

-0.61

meg

-0.61

::::::::

-0.60

 Tradable

-0.58

POSITIVE LOGITS

SF

0.75

utter

0.74

yon

0.71

atten

0.69

aney

0.68

assi

0.67

MN

0.65

wise

0.65

OH

0.65

OSE

0.65

Activations Density 0.283%

proper nouns or names ending with the letter 'K'

proper nouns, particularly names of individuals

No Comments

No Known Activations