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

0:0.09

1:0.06

2:0.08

3:0.10

4:0.08

5:0.06

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

dit

-1.97

Reviewer

-1.93

 sensibilities

-1.87

CLASSIFIED

-1.60

 millenn

-1.58

 unemploy

-1.53

comings

-1.50

luster

-1.46

ascript

-1.46

ORK

-1.45

POSITIVE LOGITS

rypt

1.77

天

1.58

�

1.54

 donate

1.53

alty

1.43

リ

1.37

affle

1.36

 Bloomberg

1.36

チ

1.35

サ

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.