INDEX

Explanations

terms related to education and learning

oai_token-act-pair · gpt-3.5-turbo

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

senal

-0.75

abwe

-0.68

lished

-0.68

Ĥª

-0.68

berus

-0.67

 Shipping

-0.66

vati

-0.66

zzi

-0.65

tar

-0.65

swick

-0.65

POSITIVE LOGITS

 disabilities

0.92

 Curve

0.87

 curve

0.87

shire

0.84

learn

0.78

Learning

0.78

 lessons

0.76

fulness

0.75

 Clicker

0.75

 disability

0.73

Activations Density 0.027%

terms related to education and learning

No Comments

No Known Activations