INDEX

Explanations

references to awards and nominations in various entertainment industries

oai_token-act-pair · gpt-3.5-turbo

nominations and awards related to film and television

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

 Anon

-0.78

itness

-0.72

bol

-0.72

yip

-0.70

 drills

-0.70

mone

-0.67

gun

-0.67

chan

-0.67

nel

-0.66

IRT

-0.66

POSITIVE LOGITS

 nominations

1.43

 nomination

1.35

 Awards

1.22

 Award

1.21

 nominees

1.17

 nominated

1.11

Â®

1.05

 nominee

1.04

 Emmy

1.03

 award

1.02

Activations Density 0.055%

references to awards and nominations in various entertainment industries

nominations and awards related to film and television

No Comments

No Known Activations