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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

onz

-1.93

uxe

-1.74

ote

-1.70

iton

-1.69

itures

-1.68

itor

-1.67

 thereof

-1.66

 Junior

-1.65

uce

-1.65

atories

-1.63

POSITIVE LOGITS

 behavi

2.74

 predic

2.13

 millenn

2.12

 enthusi

2.05

 advoc

2.03

BIL

1.98

 Notting

1.98

 Niet

1.96

�

1.95

 proble

1.93

Activations Density 0.000%

No Known Activations

This feature has no known activations.