INDEX

Explanations

mentions of seasons within TV shows

oai_token-act-pair · gpt-3.5-turbo

mentions of television show seasons and episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ntil

-0.73

iasis

-0.73

orget

-0.72

ulic

-0.71

gencies

-0.70

yre

-0.69

cipled

-0.69

eric

-0.69

rish

-0.68

jri

-0.66

POSITIVE LOGITS

 finale

1.20

 installments

1.09

 premiere

1.05

isodes

1.02

 episodes

1.00

 Episode

0.96

 episode

0.93

 Premiere

0.92

 premie

0.92

 airing

0.91

Activations Density 0.090%

mentions of seasons within TV shows

mentions of television show seasons and episodes

No Comments

No Known Activations