INDEX

Explanations

No Explanations Found

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

Fighting

-0.65

rov

-0.64

á

-0.63

paio

-0.63

aii

-0.62

rero

-0.61

 fighting

-0.61

 srfAttach

-0.60

iety

-0.59

Subscribe

-0.58

POSITIVE LOGITS

BuyableInstoreAndOnline

0.93

flies

0.87

hower

0.77

noon

0.75

lees

0.69

iaz

0.67

wings

0.67

Interstitial

0.67

Wem

0.65

 Takeru

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.