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

0:0.10

1:0.07

2:0.09

3:0.07

4:0.08

5:0.10

6:0.07

7:0.06

8:0.07

9:0.10

10:0.07

11:0.08

Negative Logits

 Kern

-1.81

 Debor

-1.81

 Ashton

-1.77

Kut

-1.76

 Moff

-1.76

 Schmidt

-1.70

 Blackburn

-1.70

 Spit

-1.67

 Stanton

-1.62

 Mell

-1.62

POSITIVE LOGITS

 compass

1.90

usterity

1.76

thood

1.75

五

1.66

soDeliveryDate

1.66

omics

1.64

 wearer

1.63

 captcha

1.62

yright

1.62

arak

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.