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

yip

-0.89

hesda

-0.72

icter

-0.72

hedral

-0.71

£ı

-0.70

 spons

-0.69

 reper

-0.68

hon

-0.68

ħĭ

-0.67

cember

-0.67

POSITIVE LOGITS

Continue

0.75

Part

0.70

again

0.69

cat

0.67

gers

0.65

input

0.65

DOI

0.65

http

0.65

Figure

0.64

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.