INDEX

Explanations

keyword "prop" and related terms

oai_token-act-pair · gpt-3.5-turbo

references to props in a cinematic or theatrical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Carbuncle

-0.86

soever

-0.73

DragonMagazine

-0.73

Interstitial

-0.68

 Intent

-0.67

 MacArthur

-0.66

Maw

-0.65

 Waters

-0.64

views

-0.63

hips

-0.63

POSITIVE LOGITS

itious

1.07

ulsive

1.06

 prop

0.98

etry

0.90

hetical

0.87

ylene

0.86

uls

0.82

ounded

0.81

onents

0.79

hetically

0.77

Activations Density 0.007%

keyword "prop" and related terms

references to props in a cinematic or theatrical context

No Comments

No Known Activations