INDEX

Explanations

phrases instructing or explaining a simple process

oai_token-act-pair · gpt-3.5-turbo

the word "Simply" and its variations used for giving instructions or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 elders

-0.70

 attendant

-0.70

 coun

-0.66

 extensively

-0.64

 patent

-0.64

 protector

-0.64

 vigorously

-0.63

egal

-0.62

 meticulously

-0.58

 particularly

-0.58

POSITIVE LOGITS

IFIED

0.87

tons

0.86

Simply

0.85

ername

0.80

reet

0.76

Login

0.75

Drag

0.75

ified

0.75

isine

0.74

reme

0.73

Activations Density 0.011%

phrases instructing or explaining a simple process

the word "Simply" and its variations used for giving instructions or explanations

No Comments

No Known Activations