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

1:0.07

2:0.07

3:0.09

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

.�

-2.03

 Indigo

-1.90

 experien

-1.87

 trave

-1.86

 commuters

-1.76

OPLE

-1.72

 mathemat

-1.71

 unaff

-1.70

 strugg

-1.69

hift

-1.68

POSITIVE LOGITS

stros

2.05

uments

2.00

oks

1.96

oval

1.87

urn

1.81

yrinth

1.75

ovo

1.71

Attach

1.65

ノ

1.63

raud

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.