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

1:0.08

2:0.07

3:0.08

4:0.10

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

 Collider

-2.07

��

-1.81

Ct

-1.69

MpServer

-1.67

 Cruel

-1.55

 Chun

-1.53

Tes

-1.52

 Coil

-1.52

 CrossRef

-1.50

��

-1.49

POSITIVE LOGITS

ounce

1.76

rio

1.66

arta

1.65

nos

1.64

thood

1.63

wine

1.59

agna

1.59

cens

1.57

SPONSORED

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.