INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ciating

-0.73

inventoryQuantity

-0.73

ysc

-0.70

mouth

-0.64

anmar

-0.62

 McCull

-0.62

xtap

-0.61

ofi

-0.61

iful

-0.60

oshenko

-0.60

POSITIVE LOGITS

resso

0.68

gnu

0.65

rahim

0.63

alsa

0.63

 Frie

0.63

VERTISEMENT

0.63

GH

0.62

 Lobby

0.62

-$

0.60

 crossover

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.