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

opausal

-0.72

 hedge

-0.66

govtrack

-0.66

axe

-0.66

hower

-0.65

iasis

-0.64

IZE

-0.64

 accelerator

-0.63

 carrot

-0.63

quet

-0.63

POSITIVE LOGITS

iHUD

0.72

escal

0.68

Syn

0.67

Night

0.66

luaj

0.66

 Session

0.65

emon

0.64

 Winds

0.64

 Courier

0.62

Mac

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.