INDEX

Explanations

numerical quantities denoting large amounts or groups of people

oai_token-act-pair · gpt-3.5-turbo

references to large quantities of people or items

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

 Silence

-0.73

odox

-0.69

 Carnage

-0.68

 Finder

-0.67

 Curious

-0.67

 Prov

-0.66

cade

-0.66

Cyn

-0.65

 Selection

-0.64

 Trader

-0.64

POSITIVE LOGITS

 pounds

0.95

 dollars

0.91

ourcing

0.70

lbs

0.69

 gallons

0.69

lbs

0.68

ourced

0.68

 kilograms

0.68

dollar

0.68

uid

0.66

Activations Density 0.089%

numerical quantities denoting large amounts or groups of people

references to large quantities of people or items

No Comments

No Known Activations