INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sense

-0.90

ovember

-0.85

 Shame

-0.78

 perk

-0.77

ensical

-0.69

 Hats

-0.67

 derogatory

-0.67

faces

-0.66

 Masquerade

-0.66

 Reve

-0.65

POSITIVE LOGITS

alyses

0.73

////////////////

0.68

NAD

0.67

iatus

0.66

adle

0.66

////////

0.66

ãĥīãĥ©

0.66

prototype

0.64

 delta

0.64

ãĤ»

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.