INDEX

Explanations

verbs/actions related to online activities or transactions

oai_token-act-pair · gpt-3.5-turbo

verbs and actions related to interactions and transactions

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

taboola

-0.76

thur

-0.74

brew

-0.70

berra

-0.68

Enlarge

-0.67

nets

-0.63

Nit

-0.63

emonic

-0.62

hon

-0.60

NBC

-0.59

POSITIVE LOGITS

 oneself

0.67

 Colossus

0.65

 safely

0.62

 anyway

0.62

rul

0.60

 theirs

0.60

alogue

0.60

 badly

0.60

 yours

0.60

 horizont

0.60

Activations Density 0.966%

verbs/actions related to online activities or transactions

verbs and actions related to interactions and transactions

No Comments

No Known Activations