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

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.08

11:0.09

Negative Logits

ither

-1.82

ourning

-1.74

entin

-1.74

izons

-1.66

oba

-1.60

xes

-1.52

olphins

-1.51

 Nano

-1.50

ichever

-1.49

 Fiscal

-1.49

POSITIVE LOGITS

��

1.94

rul

1.80

 confir

1.69

bug

1.65

 disapp

1.65

 advoc

1.65

 agre

1.63

"""

1.63

 implication

1.63

 hoax

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.