INDEX

Explanations

phrases related to eligibility and qualifying for something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate eligibility or qualification criteria for certain programs or benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

liness

-0.80

imgur

-0.70

clock

-0.66

ern

-0.64

hed

-0.62

killing

-0.62

down

-0.61

isms

-0.61

weak

-0.61

hearted

-0.61

POSITIVE LOGITS

 Medicaid

0.85

ADA

0.82

thood

0.78

 Survivor

0.75

 exemptions

0.75

ADRA

0.75

AFTA

0.74

 parole

0.74

 discounted

0.70

ĨĴ

0.70

Activations Density 0.138%

phrases related to eligibility and qualifying for something

phrases that indicate eligibility or qualification criteria for certain programs or benefits

No Comments

No Known Activations