INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

alach

-0.79

icago

-0.76

law

-0.72

rodu

-0.70

atti

-0.68

leased

-0.66

intend

-0.65

trade

-0.65

outheast

-0.64

arium

-0.63

POSITIVE LOGITS

æ©Ł

0.74

jah

0.74

ç¥ŀ

0.68

åī

0.68

âĶĢâĶĢâĶĢâĶĢ

0.67

hess

0.64

FIG

0.64

TABLE

0.64

 regiment

0.62

çĶ°

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.