INDEX

Explanations

expressions that denote a large or significant amount

oai_token-act-pair · gpt-3.5-turbo

emphasized words indicating large quantities or high values

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

 livest

-0.87

relations

-0.74

 Dise

-0.71

 Reincarn

-0.70

rative

-0.67

thood

-0.66

aded

-0.64

astery

-0.64

sych

-0.64

lict

-0.63

POSITIVE LOGITS

 hefty

0.85

 chunk

0.79

 whopping

0.78

pole

0.71

ï¸ı

0.71

ãĤĮ

0.67

bilt

0.67

 Rack

0.67

 slate

0.65

 notch

0.64

Activations Density 0.046%

expressions that denote a large or significant amount

emphasized words indicating large quantities or high values

No Comments

No Known Activations