INDEX

Explanations

instances where something is stated to have a right or permission to do something

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of entitlement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

eda

-0.71

à©

-0.70

midt

-0.67

ello

-0.67

 Kenobi

-0.67

à¨

-0.64

edia

-0.64

etta

-0.63

 Marino

-0.63

JM

-0.62

POSITIVE LOGITS

leness

0.94

 entitle

0.88

 entitled

0.85

ividual

0.82

itled

0.81

Reviewer

0.78

 entit

0.77

ments

0.77

stract

0.76

ngth

0.76

Activations Density 0.007%

instances where something is stated to have a right or permission to do something

terms related to the concept of entitlement

No Comments

No Known Activations