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

0:0.08

1:0.05

2:0.07

3:0.09

4:0.08

5:0.09

6:0.08

7:0.06

8:0.07

9:0.10

10:0.09

11:0.08

Negative Logits

liest

-1.66

 Blazers

-1.62

 rall

-1.62

anchester

-1.62

angular

-1.51

 Indigenous

-1.48

Gallery

-1.46

ovych

-1.46

oots

-1.43

eless

-1.41

POSITIVE LOGITS

 drip

1.61

�

1.59

cpu

1.57

DIT

1.56

IPM

1.52

 heater

1.49

 wifi

1.49

AIN

1.48

 regrets

1.42

FTWARE

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.