INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 staples

-0.73

 Scandinavian

-0.70

artifacts

-0.67

heon

-0.66

lectic

-0.65

 Hispanic

-0.65

apers

-0.65

icio

-0.64

itates

-0.61

 Gothic

-0.61

POSITIVE LOGITS

ãĤ±

0.77

catentry

0.72

 tremend

0.69

soDeliveryDate

0.68

context

0.67

zinski

0.66

dylib

0.65

ãĥķãĤ©

0.64

 GOODMAN

0.64

ãĥĩãĤ£

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.