INDEX

Explanations

references to news articles or reported incidents involving specific individuals

oai_token-act-pair · gpt-3.5-turbo

terms related to journalism and reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaver

-0.59

VERTISEMENT

-0.57

emonium

-0.56

 =================================================================

-0.54

ertodd

-0.53

 =================================

-0.53

 Logged

-0.52

ificent

-0.52

=-=-=-=-=-=-=-=-

-0.51

".[

-0.51

POSITIVE LOGITS

 debts

0.68

 grievances

0.66

existent

0.64

ById

0.62

 objections

0.62

 inconvenient

0.61

 weakness

0.61

 injust

0.61

 pesky

0.59

 commandments

0.58

Activations Density 1.171%

references to news articles or reported incidents involving specific individuals

terms related to journalism and reporting

No Comments

No Known Activations