INDEX

Explanations

information related to box office performances

oai_token-act-pair · gpt-3.5-turbo

monetary values and box office performance indicators related to films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

CHAT

-0.87

 schematic

-0.77

seless

-0.73

afety

-0.73

 Administ

-0.71

 informants

-0.70

 admins

-0.69

 tolerated

-0.69

plain

-0.69

 sche

-0.68

POSITIVE LOGITS

 theaters

1.24

gross

1.19

 domestically

1.15

 Cinema

1.12

 Paramount

1.11

 Cannes

1.04

 sequels

1.03

 Deadpool

1.02

 gross

1.02

 cinem

0.98

Activations Density 0.239%

information related to box office performances

monetary values and box office performance indicators related to films

No Comments

No Known Activations