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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.09

3:0.09

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

reply

-1.85

 merit

-1.80

 Cheong

-1.67

ranch

-1.60

 cause

-1.58

 mistaken

-1.56

 Granger

-1.52

agon

-1.51

ye

-1.50

 Sherman

-1.49

POSITIVE LOGITS

ftime

2.54

yna

2.21

querque

2.09

eteria

1.83

oaded

1.81

�醒

1.81

estyles

1.76

ISO

1.75

actionDate

1.74

 Agric

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.