INDEX

Explanations

references to the concept of privilege

oai_token-act-pair · gpt-3.5-turbo

references to privilege and entitlement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ood

-0.83

tra

-0.80

agh

-0.72

Interstitial

-0.72

thumbnails

-0.72

GH

-0.69

tered

-0.68

itate

-0.66

arre

-0.66

urgy

-0.66

POSITIVE LOGITS

ilege

1.42

 privilege

1.18

ileged

1.16

 afforded

0.97

 holders

0.94

 conferred

0.89

 Priv

0.85

 bestowed

0.84

 privileges

0.82

 holder

0.82

Activations Density 0.053%

references to the concept of privilege

references to privilege and entitlement

No Comments

No Known Activations