INDEX

Explanations

mentions of royalty, monarchs, and related terms

oai_token-act-pair · gpt-3.5-turbo

references to monarchies and related terms

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

ãĤ©

-0.75

OUT

-0.72

 Lank

-0.71

kr

-0.71

 Loaded

-0.71

lder

-0.70

lar

-0.68

butt

-0.67

TING

-0.67

Gi

-0.67

POSITIVE LOGITS

 monarch

1.00

ical

0.92

 Seym

0.90

 monarchy

0.89

 butterflies

0.87

istry

0.84

 butterfly

0.82

reditary

0.81

mares

0.81

 presided

0.79

Activations Density 0.031%

mentions of royalty, monarchs, and related terms

references to monarchies and related terms

No Comments

No Known Activations