INDEX

Explanations

terms related to internet policy focusing on net neutrality

oai_token-act-pair · gpt-3.5-turbo

references to net neutrality and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Building

-0.70

sa

-0.69

GM

-0.69

Produ

-0.68

Attempts

-0.68

orian

-0.67

URE

-0.66

Inst

-0.66

Jen

-0.66

NT

-0.65

POSITIVE LOGITS

 neutrality

1.33

 creeps

0.84

yip

0.83

 footing

0.82

anship

0.81

 buffs

0.77

 lane

0.77

ichick

0.76

 desks

0.76

jriwal

0.75

Activations Density 0.006%

terms related to internet policy focusing on net neutrality

references to net neutrality and related terms

No Comments

No Known Activations