INDEX

Explanations

mentions of health insurance-related terms and affordability issues

oai_token-act-pair · gpt-3.5-turbo

terms related to health insurance and coverage issues

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

 Hacker

-0.61

ockey

-0.59

Brew

-0.58

Nit

-0.58

Beer

-0.57

 Gundam

-0.57

ieft

-0.56

 Interpret

-0.55

Panel

-0.55

 Hunting

-0.55

POSITIVE LOGITS

 safely

1.03

 lawfully

0.98

 unlawfully

0.94

 sooner

0.90

 abroad

0.87

 regardless

0.87

 outdoors

0.86

 professionally

0.86

 legitimately

0.84

 responsibly

0.84

Activations Density 0.487%

mentions of health insurance-related terms and affordability issues

terms related to health insurance and coverage issues

No Comments

No Known Activations