INDEX

Explanations

phrases indicating the act of acquiring new knowledge or skills

oai_token-act-pair · gpt-3.5-turbo

instances of the word "learn."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ded

-0.72

pled

-0.68

AMI

-0.68

 ï¿½

-0.67

Dak

-0.67

issions

-0.64

 tightly

-0.64

adal

-0.64

 headed

-0.63

berman

-0.63

POSITIVE LOGITS

learn

1.07

Lear

1.03

¿½

0.90

Learning

0.87

ĨĴ

0.86

Learn

0.86

 Learn

0.81

ģ«

0.81

 learns

0.79

 learn

0.76

Activations Density 0.018%

phrases indicating the act of acquiring new knowledge or skills

instances of the word "learn."

No Comments

No Known Activations