INDEX

Explanations

legal and policy-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to legislation and legal processes

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

ĪĴ

-0.71

Redd

-0.60

 Vill

-0.59

ync

-0.59

 ILCS

-0.58

essions

-0.58

 Undead

-0.58

Rust

-0.57

DragonMagazine

-0.57

yrics

-0.55

POSITIVE LOGITS

 itself

0.99

 acronym

0.67

's

0.64

 orally

0.62

 unfold

0.62

 beforehand

0.60

iverse

0.59

ulus

0.58

 himself

0.58

 amounted

0.57

Activations Density 0.365%

legal and policy-related terms

terms related to legislation and legal processes

No Comments

No Known Activations