INDEX

Explanations

references to television show seasons

oai_token-act-pair · gpt-3.5-turbo

references to the seasons of television shows

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

artisan

-0.73

gencies

-0.71

orget

-0.71

istani

-0.70

ogle

-0.70

yre

-0.65

committee

-0.65

 hemorrh

-0.64

uckland

-0.64

ronics

-0.64

POSITIVE LOGITS

 finale

1.31

 premiere

1.06

 opener

0.93

 premie

0.86

 premiered

0.82

 aired

0.81

 Premiere

0.80

DVD

0.79

 airing

0.79

ÃįÃį

0.79

Activations Density 0.034%

references to television show seasons

references to the seasons of television shows

No Comments

No Known Activations