INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.05

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.08

8:0.10

9:0.07

10:0.08

11:0.08

Negative Logits

 Kinder

-1.64

 smarter

-1.57

 Products

-1.54

awed

-1.52

acters

-1.52

breeding

-1.51

aid

-1.50

 affecting

-1.49

 additive

-1.45

rogram

-1.45

POSITIVE LOGITS

�

2.24

BuyableInstoreAndOnline

2.02

田

2.01

Interstitial

1.93

ModLoader

1.84

 horizont

1.82

▒

1.73

龍喚士

1.72

inventoryQuantity

1.70

ADRA

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.