INDEX

Explanations

mentions of legal or ethical responsibilities

oai_token-act-pair · gpt-3.5-turbo

words that refer to obligations and responsibilities

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

vill

-0.79

atin

-0.77

vae

-0.75

hematic

-0.71

visors

-0.70

auder

-0.68

 Spray

-0.68

oco

-0.67

stocks

-0.67

ican

-0.66

POSITIVE LOGITS

 obligation

1.16

 obliged

1.12

 obligations

1.10

 obligated

1.01

 owed

0.93

 oblig

0.81

 forgiveness

0.81

 Compliance

0.77

 incurred

0.76

 commitments

0.76

Activations Density 0.022%

mentions of legal or ethical responsibilities

words that refer to obligations and responsibilities

No Comments

No Known Activations