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

çĭ

-0.83

heter

-0.72

Icon

-0.68

colour

-0.67

ĨĴ

-0.65

gb

-0.65

onga

-0.64

à

-0.64

Euro

-0.64

horn

-0.63

POSITIVE LOGITS

heimer

0.72

 Drinking

0.71

 answer

0.66

fall

0.63

 listeners

0.62

ugal

0.62

 listener

0.62

 Subst

0.61

 Malf

0.61

 unde

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.