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

nuts

-0.70

Nor

-0.64

 Puzzles

-0.64

Oak

-0.63

insk

-0.63

 Merchants

-0.62

Spot

-0.61

terness

-0.60

 Suffolk

-0.59

POSITIVE LOGITS

 waiver

0.77

 waivers

0.68

uler

0.65

qq

0.63

ãģ¦

0.62

 passport

0.62

 modem

0.61

 fian

0.60

 fluids

0.60

 narrowly

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.