INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĥ¼ãĥ³

-0.54

eco

-0.44

ahime

-0.44

ality

-0.43

ãĤ¨ãĥ«

-0.42

ãĥ³

-0.41

ãĤ³

-0.40

ãĥķãĤ¡

-0.40

ãĤ±

-0.40

 sanctuary

-0.40

POSITIVE LOGITS

%%%%

0.53

âĢ¢âĢ¢âĢ¢âĢ¢

0.49

 Picture

0.48

[/

0.47

 Wage

0.45

kefeller

0.45

=~=~

0.45

-+

0.44

param

0.44

Ì¶

0.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.