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

0:0.10

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.06

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

lights

-1.99

Ven

-1.71

straight

-1.64

 Ichigo

-1.60

 Cher

-1.59

Lex

-1.58

 Hearth

-1.57

meet

-1.52

Bud

-1.51

Personal

-1.50

POSITIVE LOGITS

otype

2.12

ulz

1.86

oğ

1.78

essor

1.67

isf

1.67

otypes

1.67

 GABA

1.64

stadt

1.61

 indexed

1.57

 inhibit

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.