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

APD

-0.81

ablishment

-0.79

VID

-0.74

KR

-0.72

igmat

-0.69

riction

-0.68

Buyable

-0.67

 Skydragon

-0.67

ibl

-0.66

Values

-0.66

POSITIVE LOGITS

conservancy

0.72

 liner

0.71

dump

0.67

cess

0.65

etheless

0.64

ycle

0.63

 refuel

0.62

reply

0.62

onite

0.61

bring

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.