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

xual

-0.83

ministic

-0.75

acci

-0.74

 scaff

-0.70

odynam

-0.68

omorphic

-0.67

zsche

-0.67

ffe

-0.66

cean

-0.64

 Mechanical

-0.64

POSITIVE LOGITS

ells

0.73

ãĤ¨

0.69

 Nokia

0.68

anus

0.68

-'

0.66

Nau

0.66

 Winchester

0.64

Iz

0.63

SIG

0.62

NV

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.