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

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

MF

-1.94

gallery

-1.81

Plug

-1.76

Tags

-1.75

MD

-1.66

hor

-1.61

usb

-1.56

Plugin

-1.54

nec

-1.54

ODUCT

-1.53

POSITIVE LOGITS

 Macron

1.74

 Oswald

1.74

 cooperating

1.73

 contradicted

1.60

Yel

1.58

 behaved

1.54

 Franco

1.52

 deposited

1.50

 stabilized

1.49

 accum

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.