INDEX

Explanations

phrases related to the financial success or performance of movies, particularly focusing on box office figures

oai_token-act-pair · gpt-3.5-turbo

references to box office performance and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pod

-0.74

ndra

-0.70

 Labrador

-0.68

onomous

-0.63

 Hast

-0.62

Pod

-0.62

lis

-0.62

Beg

-0.60

TON

-0.60

 Lerner

-0.59

POSITIVE LOGITS

 receipts

0.85

eers

0.79

 theaters

0.77

ovies

0.73

 thriller

0.71

 projections

0.71

ctors

0.70

buster

0.70

ographer

0.68

 figures

0.67

Activations Density 0.033%

phrases related to the financial success or performance of movies, particularly focusing on box office figures

references to box office performance and related terms

No Comments

No Known Activations