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

1:0.07

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.09

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

�

-1.98

 Aires

-1.80

aus

-1.79

hus

-1.74

 Unch

-1.69

angled

-1.68

 faire

-1.66

 beautiful

-1.62

hap

-1.62

Coc

-1.61

POSITIVE LOGITS

ISTER

2.10

CDC

1.86

encer

1.85

 arrives

1.79

aldi

1.78

ibus

1.76

���

1.75

earchers

1.75

neau

1.74

undown

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.