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

 canon

-0.73

 Recommended

-0.68

 odds

-0.67

 Wikipedia

-0.66

 margins

-0.65

canon

-0.64

ected

-0.64

 Rule

-0.63

 Mant

-0.61

ional

-0.61

POSITIVE LOGITS

atform

0.94

nesota

0.81

incarn

0.77

wagen

0.75

peror

0.75

guyen

0.74

olphins

0.73

Ħ¢

0.73

vasive

0.72

neum

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.