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

grounds

-0.82

uploads

-0.76

ffen

-0.69

scope

-0.67

swick

-0.67

worm

-0.66

frog

-0.65

fired

-0.65

ended

-0.65

OD

-0.64

POSITIVE LOGITS

yss

0.72

icter

0.66

ħĭ

0.64

paio

0.64

 mathemat

0.62

ibaba

0.61

ļéĨĴ

0.61

assembly

0.60

 herein

0.60

alam

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.