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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owered

-0.73

itled

-0.70

amily

-0.67

hemy

-0.65

orsche

-0.64

ongs

-0.64

retched

-0.64

milo

-0.63

cript

-0.62

ãĥ¼ãĤ¯

-0.62

POSITIVE LOGITS

 Independence

0.64

 Chal

0.64

 Delivery

0.63

 stumble

0.62

illes

0.61

 hygiene

0.61

ordan

0.59

âķĲ

0.59

 succeeding

0.58

zona

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.