INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

HTTP

-0.70

away

-0.68

aco

-0.67

OH

-0.66

too

-0.66

¶

-0.64

twitter

-0.64

Bul

-0.63

uphem

-0.62

ormal

-0.62

POSITIVE LOGITS

 Takeru

0.79

 Strateg

0.73

 Patel

0.72

onduct

0.70

 perspect

0.68

monds

0.68

depth

0.66

 Karin

0.66

 answ

0.65

 Franz

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.