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

1:0.07

2:0.09

3:0.09

4:0.09

5:0.07

6:0.06

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

)=(

-1.94

 Salvador

-1.69

 Rita

-1.65

Yam

-1.63

 Polish

-1.61

Ry

-1.57

Rub

-1.52

 Lank

-1.51

 Marie

-1.51

 Pink

-1.51

POSITIVE LOGITS

 intrins

2.00

Reviewer

1.90

 laun

1.81

vati

1.77

 Finder

1.76

 Sovere

1.76

awa

1.74

assic

1.73

LEASE

1.72

ftime

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.