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

osponsors

-0.88

ModLoader

-0.78

iqueness

-0.77

 Nightmares

-0.75

 commissions

-0.73

itially

-0.72

\",

-0.71

ĸļå£«

-0.71

ãĥ¼ãĥĨ

-0.70

lees

-0.69

POSITIVE LOGITS

odium

0.71

Xan

0.69

 panc

0.67

ram

0.67

epad

0.65

 dehyd

0.64

 Vegeta

0.63

 Taco

0.63

 burner

0.62

nib

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.