INDEX

Explanations

terms related to statistics and rankings

oai_token-act-pair · gpt-3.5-turbo

instances where "the" is used in reference to rankings, positions, or leading entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

SPONSORED

-0.87

msg

-0.77

rg

-0.72

arten

-0.71

bek

-0.67

onse

-0.66

 wisely

-0.66

edit

-0.65

lov

-0.65

abal

-0.64

POSITIVE LOGITS

 charts

1.02

 nation

0.99

 standings

0.99

 heap

0.96

 rankings

0.95

 pack

0.88

 hierarchy

0.88

 fray

0.88

 list

0.87

 polls

0.84

Activations Density 0.113%

terms related to statistics and rankings

instances where "the" is used in reference to rankings, positions, or leading entities

No Comments

No Known Activations