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

opa

-0.66

 troop

-0.62

 Dull

-0.61

udic

-0.60

 empt

-0.60

 troopers

-0.58

 peeled

-0.58

 ancestors

-0.57

 behaved

-0.57

 investigators

-0.56

POSITIVE LOGITS

 indu

0.68

pace

0.68

ufact

0.65

paces

0.63

JM

0.63

ploy

0.62

chant

0.62

minist

0.61

ospace

0.61

MET

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.