INDEX

Explanations

phrases related to cuts in various contexts, such as healthcare, government funding, and social programs

oai_token-act-pair · gpt-3.5-turbo

references to cuts in healthcare and social service funding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 rumours

-0.76

ether

-0.74

atta

-0.72

quickShipAvailable

-0.72

Rum

-0.68

wave

-0.67

perfect

-0.67

igmatic

-0.67

abal

-0.66

Desc

-0.65

POSITIVE LOGITS

 Medicaid

1.43

 Medicare

1.35

 programs

1.30

 pensions

1.27

 subsidies

1.19

 budgets

1.17

 infrastructure

1.07

 hospitals

1.07

 appropriations

1.07

NIH

1.06

Activations Density 0.347%

phrases related to cuts in various contexts, such as healthcare, government funding, and social programs

references to cuts in healthcare and social service funding

No Comments

No Known Activations