INDEX

Explanations

mentions of the term "mandate" in various contexts, particularly related to laws or regulations

oai_token-act-pair · gpt-3.5-turbo

references to the concept of a mandate, particularly in legal or policy contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

istics

-0.86

stocks

-0.79

vae

-0.79

ãģį

-0.76

folk

-0.74

esta

-0.72

Ñĭ

-0.70

gar

-0.70

hop

-0.70

angers

-0.69

POSITIVE LOGITS

 mandate

0.91

 mandates

0.79

 imposed

0.77

 mandated

0.75

 creep

0.75

 requirement

0.73

 mand

0.71

eers

0.71

 compel

0.68

 compliance

0.67

Activations Density 0.014%

mentions of the term "mandate" in various contexts, particularly related to laws or regulations

references to the concept of a mandate, particularly in legal or policy contexts

No Comments

No Known Activations