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

iths

-0.88

rake

-0.78

oration

-0.77

ciating

-0.73

eering

-0.71

wagen

-0.69

athering

-0.68

asting

-0.67

omy

-0.67

nesday

-0.66

POSITIVE LOGITS

Else

0.74

 undone

0.69

adj

0.68

é¾įå¥ĳå£«

0.64

é¾įåĸļå£«

0.63

 reset

0.63

CLOSE

0.62

taboola

0.61

.ï¿½

0.60

.","

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.