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

»

-0.83

ãĥ¼ãĥĨãĤ£

-0.80

boss

-0.76

encia

-0.70

 Conversation

-0.70

ãĥ¼ãĥĨ

-0.68

ibaba

-0.67

ãĥ¤

-0.66

âĸ¬

-0.65

ais

-0.65

POSITIVE LOGITS

 regress

0.68

 sham

0.66

 circa

0.63

wcsstore

0.62

onest

0.61

eds

0.60

isms

0.60

uther

0.59

conv

0.59

stem

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.