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

uder

-0.72

tty

-0.65

maid

-0.64

buff

-0.63

 discipline

-0.63

eers

-0.62

raq

-0.62

arta

-0.62

 nurs

-0.61

fur

-0.60

POSITIVE LOGITS

lectic

0.80

imates

0.66

olition

0.65

stown

0.65

ession

0.64

ETF

0.64

 Americ

0.63

 Wells

0.62

olulu

0.62

$.

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.