INDEX

Explanations

references to different grades in an educational context

oai_token-act-pair · gpt-3.5-turbo

references to educational grades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Bundy

-0.82

eers

-0.80

pload

-0.78

othe

-0.78

orial

-0.77

ĸļ

-0.76

oÄŁ

-0.76

iversal

-0.75

sle

-0.72

icative

-0.72

POSITIVE LOGITS

 grades

0.91

 grade

0.81

 rating

0.78

 grading

0.72

 plutonium

0.70

ably

0.67

Grade

0.67

children

0.66

 ratings

0.62

fork

0.61

Activations Density 0.019%

references to different grades in an educational context

references to educational grades

No Comments

No Known Activations