INDEX

Explanations

words related to writing or columns

oai_token-act-pair · gpt-3.5-turbo

references to specific columns in a publication or series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

CRIP

-0.80

qual

-0.72

à¹

-0.67

 Romanian

-0.67

ESCO

-0.66

BLE

-0.65

 Bulg

-0.62

lder

-0.62

gets

-0.61

zie

-0.61

POSITIVE LOGITS

ists

0.95

 columns

0.94

 inches

0.86

 column

0.83

 headers

0.81

ical

0.81

istics

0.81

ftime

0.80

iers

0.78

column

0.77

Activations Density 0.016%

words related to writing or columns

references to specific columns in a publication or series

No Comments

No Known Activations