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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odox

-0.80

phasis

-0.68

è»

-0.67

alky

-0.65

ansson

-0.64

Weapons

-0.64

==

-0.63

!=

-0.63

Grid

-0.63

bg

-0.62

POSITIVE LOGITS

rite

0.75

 teasing

0.72

 catering

0.64

aukee

0.62

 cowork

0.62

 projection

0.61

oa

0.60

 Reef

0.60

kees

0.59

 Cutter

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.