INDEX

Explanations

instances where the term "taxpayers" or related terms like "taxpayer dollars" are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to taxpayers and taxpayer money

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

lime

-0.71

 Thing

-0.67

apa

-0.67

 Grind

-0.66

Vaj

-0.65

 Condition

-0.64

rush

-0.63

occ

-0.62

 Proud

-0.61

appa

-0.61

POSITIVE LOGITS

payers

1.16

 taxpayers

1.15

 taxpayer

1.06

 subsid

1.04

 dollars

0.98

 bailed

0.95

payer

0.94

 subsidized

0.91

 subsidy

0.87

ridor

0.86

Activations Density 0.014%

instances where the term "taxpayers" or related terms like "taxpayer dollars" are mentioned

references to taxpayers and taxpayer money

No Comments

No Known Activations