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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.10

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

Category

-1.86

Geh

-1.75

 Sergey

-1.72

 Gujar

-1.66

 McCarthy

-1.63

 Uzbek

-1.61

 Putin

-1.61

 UNESCO

-1.61

 guiName

-1.60

 Marino

-1.59

POSITIVE LOGITS

oult

1.88

ゴン

1.84

owe

1.75

 answ

1.74

bis

1.65

 distur

1.59

 medic

1.58

jac

1.55

 airs

1.52

 shakes

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.