INDEX

Explanations

phrases related to legal requirements or obligations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "mandatory."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stocks

-0.90

 Tycoon

-0.80

vironment

-0.78

rums

-0.76

oscope

-0.74

olph

-0.74

sight

-0.72

erie

-0.71

Ĥ¬

-0.70

bill

-0.70

POSITIVE LOGITS

 compulsory

0.91

 mandatory

0.90

 adherence

0.88

 compliance

0.88

 redund

0.87

 minimum

0.84

 schooling

0.82

 confir

0.79

 penal

0.78

 captcha

0.77

Activations Density 0.020%

phrases related to legal requirements or obligations

instances of the word "mandatory."

No Comments

No Known Activations