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

2:0.08

3:0.07

4:0.08

5:0.10

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Header

-1.82

 Retrieved

-1.76

 Samsung

-1.62

 originals

-1.60

Untitled

-1.58

CV

-1.57

 damaged

-1.54

neath

-1.53

 NULL

-1.52

 Carrier

-1.51

POSITIVE LOGITS

HUD

1.92

gel

1.84

uggest

1.79

ヘ

1.76

ORPG

1.75

zos

1.70

 administering

1.69

byss

1.67

agents

1.66

CDC

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.