INDEX

Explanations

phrases related to the concept of learning

oai_token-act-pair · gpt-3.5-turbo

references to the concept of learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Dak

-0.67

pat

-0.66

price

-0.64

eq

-0.64

ankind

-0.63

cise

-0.63

issions

-0.61

adal

-0.61

ded

-0.61

println

-0.61

POSITIVE LOGITS

Learning

0.97

learn

0.97

 learning

0.85

inventoryQuantity

0.83

 Learning

0.81

ĨĴ

0.79

 Learn

0.78

Lear

0.77

 behavi

0.76

Learn

0.76

Activations Density 0.009%

phrases related to the concept of learning

references to the concept of learning

No Comments

No Known Activations