INDEX

Explanations

names related to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically locations and names related to places and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

CEPT

-0.69

 Medicaid

-0.68

 enrollment

-0.64

prise

-0.64

 modernization

-0.62

natureconservancy

-0.62

 definition

-0.61

 subsistence

-0.61

 attribution

-0.60

 mound

-0.60

POSITIVE LOGITS

wich

1.54

sten

0.96

pton

0.95

hal

0.94

auld

0.93

ania

0.92

ulla

0.92

ben

0.87

Īè

0.87

ethy

0.86

Activations Density 0.013%

names related to specific geographical locations

proper nouns, specifically locations and names related to places and entities

No Comments

No Known Activations