INDEX

Explanations

mentions of the term "net neutrality."

oai_token-act-pair · gpt-3.5-turbo

terms associated with net neutrality regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

FU

-0.74

yon

-0.73

orian

-0.71

Inst

-0.70

 Continental

-0.63

ha

-0.62

Sy

-0.62

inav

-0.62

NT

-0.62

Attempts

-0.62

POSITIVE LOGITS

 neutrality

1.18

 creeps

0.85

 footing

0.84

 protections

0.82

 watchdog

0.79

 regulator

0.78

 commissioners

0.77

 enforcement

0.75

 lane

0.75

 safeguards

0.74

Activations Density 0.007%

mentions of the term "net neutrality."

terms associated with net neutrality regulations

No Comments

No Known Activations