INDEX

Explanations

mentions of academic institutions and professional roles

oai_token-act-pair · gpt-3.5-turbo

references to professional roles and affiliations in academia and publishing

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

utterstock

-0.78

ettel

-0.65

 Tories

-0.64

 Canaver

-0.62

osen

-0.62

*/(

-0.59

 jurors

-0.59

 brut

-0.58

lopp

-0.58

 Britons

-0.57

POSITIVE LOGITS

Includes

0.67

 collegiate

0.61

 award

0.61

 respectively

0.60

arsity

0.60

bilt

0.59

ocument

0.58

 instructional

0.58

 educational

0.57

 Colleg

0.57

Activations Density 1.518%

mentions of academic institutions and professional roles

references to professional roles and affiliations in academia and publishing

No Comments

No Known Activations