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

liest

-0.75

anmar

-0.74

ãĥ¯

-0.73

 thor

-0.72

 Norn

-0.71

adelphia

-0.70

 Constantin

-0.70

 Pluto

-0.69

 Palest

-0.67

 cannabin

-0.67

POSITIVE LOGITS

taboola

0.79

igue

0.79

VID

0.77

ricks

0.67

 separ

0.67

clamation

0.64

 leveled

0.64

cknow

0.63

ctions

0.63

BG

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.