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

0:0.07

1:0.09

2:0.07

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

common

-1.86

 boutique

-1.69

 clos

-1.63

 strict

-1.59

 finite

-1.56

 closet

-1.55

@#&

-1.53

 discretionary

-1.50

Traditional

-1.49

 recy

-1.48

POSITIVE LOGITS

Scan

2.07

edin

1.94

Magikarp

1.89

HAHA

1.61

GAN

1.59

yip

1.58

baugh

1.58

 Grab

1.58

holm

1.57

Grab

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.