INDEX

Explanations

direct speech marked with quotations

oai_token-act-pair · gpt-3.5-turbo

dialogue punctuation, particularly the use of quotation marks

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

avorite

-0.89

irtual

-0.71

¥ŀ

-0.69

 vide

-0.68

 Lauder

-0.67

 deterrent

-0.65

 satell

-0.65

phthal

-0.64

 triv

-0.64

 subsid

-0.62

POSITIVE LOGITS

Oh

1.01

Hey

0.99

hey

0.94

Sir

0.88

Yo

0.85

0.84

cause

0.83

Everybody

0.83

Wait

0.81

Let

0.80

Activations Density 0.087%

direct speech marked with quotations

dialogue punctuation, particularly the use of quotation marks

No Comments

No Known Activations